commit 9905803b1437196ddeb99b22729a30e30dc2d144 Author: ModelHub XC Date: Mon Jun 8 20:43:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: jerryjalapeno/nart-100k-7b Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a6344aa --- /dev/null +++ b/.gitattributes @@ -0,0 +1,35 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..4d3af4d --- /dev/null +++ b/README.md @@ -0,0 +1,3 @@ +--- +license: cc-by-nc-nd-4.0 +--- diff --git a/config.json b/config.json new file mode 100644 index 0000000..4db91b4 --- /dev/null +++ b/config.json @@ -0,0 +1,23 @@ +{ + "_name_or_path": "yahma/llama-7b-hf", + "architectures": [ + "LlamaForCausalLM" + ], + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 11008, + "max_position_embeddings": 2048, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "pad_token_id": 0, + "rms_norm_eps": 1e-06, + "tie_word_embeddings": false, + "torch_dtype": "float32", + "transformers_version": "4.28.1", + "use_cache": false, + "vocab_size": 32000 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..1372199 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "pad_token_id": 0, + "transformers_version": "4.28.1" +} diff --git a/pytorch_model-00001-of-00003.bin b/pytorch_model-00001-of-00003.bin new file mode 100644 index 0000000..eeba085 --- /dev/null +++ b/pytorch_model-00001-of-00003.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29dab55544e5659cb1ea6e4f12d205829c082b5b0e7149638582799fbc9a4705 +size 9877989586 diff --git a/pytorch_model-00002-of-00003.bin b/pytorch_model-00002-of-00003.bin new file mode 100644 index 0000000..9b6a70a --- /dev/null +++ b/pytorch_model-00002-of-00003.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b5244fd10375225c830ef2dc6274b14ef931734e3ac9b3af2a933f17b62be7c +size 9894801014 diff --git a/pytorch_model-00003-of-00003.bin b/pytorch_model-00003-of-00003.bin new file mode 100644 index 0000000..6a7dd47 --- /dev/null +++ b/pytorch_model-00003-of-00003.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:099fbcc06f5e2c9903a44d5568741c023b46b59ac605dac6b40962440982f241 +size 7180990649 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000..3478b35 --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1,330 @@ +{ + "metadata": { + "total_size": 26953670656 + }, + "weight_map": { + "lm_head.weight": "pytorch_model-00003-of-00003.bin", + "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin", + "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin", + "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", + "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", + "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", + "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", + "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", + "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", + "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", + "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin", + "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin", + "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin", + "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin", + "model.norm.weight": "pytorch_model-00003-of-00003.bin" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..09a41a3 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,6 @@ +{ + "bos_token": "", + "eos_token": "", + "pad_token": "", + "unk_token": "" +} diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..6c00c74 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347 +size 499723 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..5ab645d --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,34 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "bos_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "clean_up_tokenization_spaces": false, + "eos_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "model_max_length": 2048, + "pad_token": null, + "padding_side": "right", + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizer", + "unk_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + } +} diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000..6d43713 --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,6847 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 2.9975284231339594, + "global_step": 1137, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 5.714285714285715e-07, + "loss": 1.4043, + "step": 1 + }, + { + "epoch": 0.01, + "learning_rate": 1.142857142857143e-06, + "loss": 1.417, + "step": 2 + }, + { + "epoch": 0.01, + "learning_rate": 1.7142857142857145e-06, + "loss": 1.1751, + "step": 3 + }, + { + "epoch": 0.01, + "learning_rate": 2.285714285714286e-06, + "loss": 1.1518, + "step": 4 + }, + { + "epoch": 0.01, + "learning_rate": 2.8571428571428573e-06, + "loss": 1.1192, + "step": 5 + }, + { + "epoch": 0.02, + "learning_rate": 3.428571428571429e-06, + "loss": 1.0952, + "step": 6 + }, + { + "epoch": 0.02, + "learning_rate": 4.000000000000001e-06, + "loss": 1.0354, + "step": 7 + }, + { + "epoch": 0.02, + "learning_rate": 4.571428571428572e-06, + "loss": 1.016, + "step": 8 + }, + { + "epoch": 0.02, + "learning_rate": 5.142857142857142e-06, + "loss": 0.9737, + "step": 9 + }, + { + "epoch": 0.03, + "learning_rate": 5.7142857142857145e-06, + "loss": 0.9711, + "step": 10 + }, + { + "epoch": 0.03, + "learning_rate": 6.285714285714286e-06, + "loss": 0.9546, + "step": 11 + }, + { + "epoch": 0.03, + "learning_rate": 6.857142857142858e-06, + "loss": 0.9303, + "step": 12 + }, + { + "epoch": 0.03, + "learning_rate": 7.428571428571429e-06, + "loss": 0.9083, + "step": 13 + }, + { + "epoch": 0.04, + "learning_rate": 8.000000000000001e-06, + "loss": 0.9051, + "step": 14 + }, + { + "epoch": 0.04, + "learning_rate": 8.571428571428571e-06, + "loss": 0.8831, + "step": 15 + }, + { + "epoch": 0.04, + "learning_rate": 9.142857142857144e-06, + "loss": 0.877, + "step": 16 + }, + { + "epoch": 0.04, + "learning_rate": 9.714285714285715e-06, + "loss": 0.873, + "step": 17 + }, + { + "epoch": 0.05, + "learning_rate": 1.0285714285714285e-05, + "loss": 0.8656, + "step": 18 + }, + { + "epoch": 0.05, + "learning_rate": 1.0857142857142858e-05, + "loss": 0.8567, + "step": 19 + }, + { + "epoch": 0.05, + "learning_rate": 1.1428571428571429e-05, + "loss": 0.845, + "step": 20 + }, + { + "epoch": 0.06, + "learning_rate": 1.2e-05, + "loss": 0.8401, + "step": 21 + }, + { + "epoch": 0.06, + "learning_rate": 1.2571428571428572e-05, + "loss": 0.8368, + "step": 22 + }, + { + "epoch": 0.06, + "learning_rate": 1.3142857142857145e-05, + "loss": 0.8391, + "step": 23 + }, + { + "epoch": 0.06, + "learning_rate": 1.3714285714285716e-05, + "loss": 0.8185, + "step": 24 + }, + { + "epoch": 0.07, + "learning_rate": 1.4285714285714287e-05, + "loss": 0.8262, + "step": 25 + }, + { + "epoch": 0.07, + "learning_rate": 1.4857142857142858e-05, + "loss": 0.8151, + "step": 26 + }, + { + "epoch": 0.07, + "learning_rate": 1.542857142857143e-05, + "loss": 0.817, + "step": 27 + }, + { + "epoch": 0.07, + "learning_rate": 1.6000000000000003e-05, + "loss": 0.8086, + "step": 28 + }, + { + "epoch": 0.08, + "learning_rate": 1.6571428571428574e-05, + "loss": 0.7952, + "step": 29 + }, + { + "epoch": 0.08, + "learning_rate": 1.7142857142857142e-05, + "loss": 0.8136, + "step": 30 + }, + { + "epoch": 0.08, + "learning_rate": 1.7714285714285717e-05, + "loss": 0.7942, + "step": 31 + }, + { + "epoch": 0.08, + "learning_rate": 1.8285714285714288e-05, + "loss": 0.7942, + "step": 32 + }, + { + "epoch": 0.09, + "learning_rate": 1.885714285714286e-05, + "loss": 0.7965, + "step": 33 + }, + { + "epoch": 0.09, + "learning_rate": 1.942857142857143e-05, + "loss": 0.7875, + "step": 34 + }, + { + "epoch": 0.09, + "learning_rate": 2e-05, + "loss": 0.7844, + "step": 35 + }, + { + "epoch": 0.09, + "learning_rate": 1.999995936443837e-05, + "loss": 0.7812, + "step": 36 + }, + { + "epoch": 0.1, + "learning_rate": 1.9999837458083738e-05, + "loss": 0.7844, + "step": 37 + }, + { + "epoch": 0.1, + "learning_rate": 1.999963428192684e-05, + "loss": 0.7829, + "step": 38 + }, + { + "epoch": 0.1, + "learning_rate": 1.999934983761892e-05, + "loss": 0.7707, + "step": 39 + }, + { + "epoch": 0.11, + "learning_rate": 1.999898412747168e-05, + "loss": 0.7703, + "step": 40 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998537154457298e-05, + "loss": 0.7724, + "step": 41 + }, + { + "epoch": 0.11, + "learning_rate": 1.9998008922208364e-05, + "loss": 0.7745, + "step": 42 + }, + { + "epoch": 0.11, + "learning_rate": 1.9997399435017893e-05, + "loss": 0.7595, + "step": 43 + }, + { + "epoch": 0.12, + "learning_rate": 1.9996708697839244e-05, + "loss": 0.7686, + "step": 44 + }, + { + "epoch": 0.12, + "learning_rate": 1.999593671628612e-05, + "loss": 0.7669, + "step": 45 + }, + { + "epoch": 0.12, + "learning_rate": 1.99950834966325e-05, + "loss": 0.7627, + "step": 46 + }, + { + "epoch": 0.12, + "learning_rate": 1.99941490458126e-05, + "loss": 0.7551, + "step": 47 + }, + { + "epoch": 0.13, + "learning_rate": 1.9993133371420807e-05, + "loss": 0.7633, + "step": 48 + }, + { + "epoch": 0.13, + "learning_rate": 1.9992036481711618e-05, + "loss": 0.768, + "step": 49 + }, + { + "epoch": 0.13, + "learning_rate": 1.9990858385599576e-05, + "loss": 0.7676, + "step": 50 + }, + { + "epoch": 0.13, + "learning_rate": 1.9989599092659207e-05, + "loss": 0.7513, + "step": 51 + }, + { + "epoch": 0.14, + "learning_rate": 1.998825861312492e-05, + "loss": 0.7466, + "step": 52 + }, + { + "epoch": 0.14, + "learning_rate": 1.9986836957890947e-05, + "loss": 0.758, + "step": 53 + }, + { + "epoch": 0.14, + "learning_rate": 1.998533413851124e-05, + "loss": 0.7506, + "step": 54 + }, + { + "epoch": 0.14, + "learning_rate": 1.9983750167199377e-05, + "loss": 0.7513, + "step": 55 + }, + { + "epoch": 0.15, + "learning_rate": 1.9982085056828476e-05, + "loss": 0.7544, + "step": 56 + }, + { + "epoch": 0.15, + "learning_rate": 1.9980338820931074e-05, + "loss": 0.7539, + "step": 57 + }, + { + "epoch": 0.15, + "learning_rate": 1.9978511473699024e-05, + "loss": 0.7503, + "step": 58 + }, + { + "epoch": 0.16, + "learning_rate": 1.9976603029983383e-05, + "loss": 0.7426, + "step": 59 + }, + { + "epoch": 0.16, + "learning_rate": 1.997461350529429e-05, + "loss": 0.7501, + "step": 60 + }, + { + "epoch": 0.16, + "learning_rate": 1.997254291580083e-05, + "loss": 0.7438, + "step": 61 + }, + { + "epoch": 0.16, + "learning_rate": 1.9970391278330923e-05, + "loss": 0.7458, + "step": 62 + }, + { + "epoch": 0.17, + "learning_rate": 1.9968158610371164e-05, + "loss": 0.7547, + "step": 63 + }, + { + "epoch": 0.17, + "learning_rate": 1.99658449300667e-05, + "loss": 0.746, + "step": 64 + }, + { + "epoch": 0.17, + "learning_rate": 1.9963450256221066e-05, + "loss": 0.7367, + "step": 65 + }, + { + "epoch": 0.17, + "learning_rate": 1.996097460829605e-05, + "loss": 0.7461, + "step": 66 + }, + { + "epoch": 0.18, + "learning_rate": 1.9958418006411522e-05, + "loss": 0.7442, + "step": 67 + }, + { + "epoch": 0.18, + "learning_rate": 1.9955780471345265e-05, + "loss": 0.7433, + "step": 68 + }, + { + "epoch": 0.18, + "learning_rate": 1.995306202453283e-05, + "loss": 0.7421, + "step": 69 + }, + { + "epoch": 0.18, + "learning_rate": 1.9950262688067334e-05, + "loss": 0.7416, + "step": 70 + }, + { + "epoch": 0.19, + "learning_rate": 1.99473824846993e-05, + "loss": 0.7374, + "step": 71 + }, + { + "epoch": 0.19, + "learning_rate": 1.9944421437836466e-05, + "loss": 0.7382, + "step": 72 + }, + { + "epoch": 0.19, + "learning_rate": 1.9941379571543597e-05, + "loss": 0.7431, + "step": 73 + }, + { + "epoch": 0.2, + "learning_rate": 1.9938256910542276e-05, + "loss": 0.7385, + "step": 74 + }, + { + "epoch": 0.2, + "learning_rate": 1.993505348021072e-05, + "loss": 0.7432, + "step": 75 + }, + { + "epoch": 0.2, + "learning_rate": 1.9931769306583568e-05, + "loss": 0.7322, + "step": 76 + }, + { + "epoch": 0.2, + "learning_rate": 1.992840441635167e-05, + "loss": 0.7396, + "step": 77 + }, + { + "epoch": 0.21, + "learning_rate": 1.9924958836861865e-05, + "loss": 0.7436, + "step": 78 + }, + { + "epoch": 0.21, + "learning_rate": 1.9921432596116763e-05, + "loss": 0.7413, + "step": 79 + }, + { + "epoch": 0.21, + "learning_rate": 1.991782572277452e-05, + "loss": 0.7385, + "step": 80 + }, + { + "epoch": 0.21, + "learning_rate": 1.99141382461486e-05, + "loss": 0.7323, + "step": 81 + }, + { + "epoch": 0.22, + "learning_rate": 1.9910370196207545e-05, + "loss": 0.7277, + "step": 82 + }, + { + "epoch": 0.22, + "learning_rate": 1.9906521603574713e-05, + "loss": 0.7288, + "step": 83 + }, + { + "epoch": 0.22, + "learning_rate": 1.990259249952805e-05, + "loss": 0.7276, + "step": 84 + }, + { + "epoch": 0.22, + "learning_rate": 1.9898582915999834e-05, + "loss": 0.7291, + "step": 85 + }, + { + "epoch": 0.23, + "learning_rate": 1.989449288557639e-05, + "loss": 0.7174, + "step": 86 + }, + { + "epoch": 0.23, + "learning_rate": 1.9890322441497857e-05, + "loss": 0.7335, + "step": 87 + }, + { + "epoch": 0.23, + "learning_rate": 1.9886071617657906e-05, + "loss": 0.7376, + "step": 88 + }, + { + "epoch": 0.23, + "learning_rate": 1.988174044860346e-05, + "loss": 0.7308, + "step": 89 + }, + { + "epoch": 0.24, + "learning_rate": 1.9877328969534413e-05, + "loss": 0.7304, + "step": 90 + }, + { + "epoch": 0.24, + "learning_rate": 1.9872837216303353e-05, + "loss": 0.7251, + "step": 91 + }, + { + "epoch": 0.24, + "learning_rate": 1.9868265225415263e-05, + "loss": 0.7372, + "step": 92 + }, + { + "epoch": 0.25, + "learning_rate": 1.9863613034027224e-05, + "loss": 0.7293, + "step": 93 + }, + { + "epoch": 0.25, + "learning_rate": 1.9858880679948122e-05, + "loss": 0.7286, + "step": 94 + }, + { + "epoch": 0.25, + "learning_rate": 1.9854068201638327e-05, + "loss": 0.7377, + "step": 95 + }, + { + "epoch": 0.25, + "learning_rate": 1.9849175638209393e-05, + "loss": 0.7208, + "step": 96 + }, + { + "epoch": 0.26, + "learning_rate": 1.9844203029423733e-05, + "loss": 0.7279, + "step": 97 + }, + { + "epoch": 0.26, + "learning_rate": 1.983915041569429e-05, + "loss": 0.7242, + "step": 98 + }, + { + "epoch": 0.26, + "learning_rate": 1.9834017838084234e-05, + "loss": 0.7255, + "step": 99 + }, + { + "epoch": 0.26, + "learning_rate": 1.9828805338306595e-05, + "loss": 0.7252, + "step": 100 + }, + { + "epoch": 0.27, + "learning_rate": 1.9823512958723942e-05, + "loss": 0.7376, + "step": 101 + }, + { + "epoch": 0.27, + "learning_rate": 1.981814074234804e-05, + "loss": 0.7278, + "step": 102 + }, + { + "epoch": 0.27, + "learning_rate": 1.9812688732839497e-05, + "loss": 0.7249, + "step": 103 + }, + { + "epoch": 0.27, + "learning_rate": 1.9807156974507403e-05, + "loss": 0.7308, + "step": 104 + }, + { + "epoch": 0.28, + "learning_rate": 1.9801545512308982e-05, + "loss": 0.7343, + "step": 105 + }, + { + "epoch": 0.28, + "learning_rate": 1.9795854391849217e-05, + "loss": 0.7273, + "step": 106 + }, + { + "epoch": 0.28, + "learning_rate": 1.979008365938048e-05, + "loss": 0.7322, + "step": 107 + }, + { + "epoch": 0.28, + "learning_rate": 1.978423336180217e-05, + "loss": 0.7298, + "step": 108 + }, + { + "epoch": 0.29, + "learning_rate": 1.9778303546660304e-05, + "loss": 0.7199, + "step": 109 + }, + { + "epoch": 0.29, + "learning_rate": 1.977229426214716e-05, + "loss": 0.7206, + "step": 110 + }, + { + "epoch": 0.29, + "learning_rate": 1.976620555710087e-05, + "loss": 0.7162, + "step": 111 + }, + { + "epoch": 0.3, + "learning_rate": 1.9760037481005018e-05, + "loss": 0.7153, + "step": 112 + }, + { + "epoch": 0.3, + "learning_rate": 1.9753790083988256e-05, + "loss": 0.7169, + "step": 113 + }, + { + "epoch": 0.3, + "learning_rate": 1.974746341682388e-05, + "loss": 0.7223, + "step": 114 + }, + { + "epoch": 0.3, + "learning_rate": 1.9741057530929425e-05, + "loss": 0.7238, + "step": 115 + }, + { + "epoch": 0.31, + "learning_rate": 1.9734572478366244e-05, + "loss": 0.715, + "step": 116 + }, + { + "epoch": 0.31, + "learning_rate": 1.972800831183909e-05, + "loss": 0.7172, + "step": 117 + }, + { + "epoch": 0.31, + "learning_rate": 1.972136508469568e-05, + "loss": 0.7246, + "step": 118 + }, + { + "epoch": 0.31, + "learning_rate": 1.9714642850926264e-05, + "loss": 0.7185, + "step": 119 + }, + { + "epoch": 0.32, + "learning_rate": 1.9707841665163196e-05, + "loss": 0.7194, + "step": 120 + }, + { + "epoch": 0.32, + "learning_rate": 1.9700961582680476e-05, + "loss": 0.7224, + "step": 121 + }, + { + "epoch": 0.32, + "learning_rate": 1.9694002659393306e-05, + "loss": 0.7164, + "step": 122 + }, + { + "epoch": 0.32, + "learning_rate": 1.9686964951857636e-05, + "loss": 0.7211, + "step": 123 + }, + { + "epoch": 0.33, + "learning_rate": 1.9679848517269708e-05, + "loss": 0.7103, + "step": 124 + }, + { + "epoch": 0.33, + "learning_rate": 1.9672653413465584e-05, + "loss": 0.7139, + "step": 125 + }, + { + "epoch": 0.33, + "learning_rate": 1.966537969892068e-05, + "loss": 0.713, + "step": 126 + }, + { + "epoch": 0.33, + "learning_rate": 1.9658027432749293e-05, + "loss": 0.7205, + "step": 127 + }, + { + "epoch": 0.34, + "learning_rate": 1.9650596674704118e-05, + "loss": 0.7158, + "step": 128 + }, + { + "epoch": 0.34, + "learning_rate": 1.9643087485175752e-05, + "loss": 0.7269, + "step": 129 + }, + { + "epoch": 0.34, + "learning_rate": 1.963549992519223e-05, + "loss": 0.7128, + "step": 130 + }, + { + "epoch": 0.35, + "learning_rate": 1.96278340564185e-05, + "loss": 0.7085, + "step": 131 + }, + { + "epoch": 0.35, + "learning_rate": 1.9620089941155945e-05, + "loss": 0.721, + "step": 132 + }, + { + "epoch": 0.35, + "learning_rate": 1.961226764234185e-05, + "loss": 0.7169, + "step": 133 + }, + { + "epoch": 0.35, + "learning_rate": 1.960436722354892e-05, + "loss": 0.7223, + "step": 134 + }, + { + "epoch": 0.36, + "learning_rate": 1.959638874898475e-05, + "loss": 0.7134, + "step": 135 + }, + { + "epoch": 0.36, + "learning_rate": 1.9588332283491297e-05, + "loss": 0.71, + "step": 136 + }, + { + "epoch": 0.36, + "learning_rate": 1.9580197892544354e-05, + "loss": 0.7096, + "step": 137 + }, + { + "epoch": 0.36, + "learning_rate": 1.957198564225304e-05, + "loss": 0.7057, + "step": 138 + }, + { + "epoch": 0.37, + "learning_rate": 1.9563695599359233e-05, + "loss": 0.711, + "step": 139 + }, + { + "epoch": 0.37, + "learning_rate": 1.9555327831237036e-05, + "loss": 0.7105, + "step": 140 + }, + { + "epoch": 0.37, + "learning_rate": 1.9546882405892247e-05, + "loss": 0.7171, + "step": 141 + }, + { + "epoch": 0.37, + "learning_rate": 1.9538359391961786e-05, + "loss": 0.7136, + "step": 142 + }, + { + "epoch": 0.38, + "learning_rate": 1.952975885871314e-05, + "loss": 0.7172, + "step": 143 + }, + { + "epoch": 0.38, + "learning_rate": 1.9521080876043816e-05, + "loss": 0.7065, + "step": 144 + }, + { + "epoch": 0.38, + "learning_rate": 1.951232551448075e-05, + "loss": 0.7064, + "step": 145 + }, + { + "epoch": 0.38, + "learning_rate": 1.9503492845179746e-05, + "loss": 0.7141, + "step": 146 + }, + { + "epoch": 0.39, + "learning_rate": 1.9494582939924908e-05, + "loss": 0.7063, + "step": 147 + }, + { + "epoch": 0.39, + "learning_rate": 1.9485595871128028e-05, + "loss": 0.714, + "step": 148 + }, + { + "epoch": 0.39, + "learning_rate": 1.9476531711828027e-05, + "loss": 0.7082, + "step": 149 + }, + { + "epoch": 0.4, + "learning_rate": 1.9467390535690343e-05, + "loss": 0.7059, + "step": 150 + }, + { + "epoch": 0.4, + "learning_rate": 1.9458172417006347e-05, + "loss": 0.7174, + "step": 151 + }, + { + "epoch": 0.4, + "learning_rate": 1.9448877430692723e-05, + "loss": 0.7118, + "step": 152 + }, + { + "epoch": 0.4, + "learning_rate": 1.9439505652290867e-05, + "loss": 0.7127, + "step": 153 + }, + { + "epoch": 0.41, + "learning_rate": 1.9430057157966272e-05, + "loss": 0.7096, + "step": 154 + }, + { + "epoch": 0.41, + "learning_rate": 1.942053202450792e-05, + "loss": 0.7051, + "step": 155 + }, + { + "epoch": 0.41, + "learning_rate": 1.9410930329327636e-05, + "loss": 0.7115, + "step": 156 + }, + { + "epoch": 0.41, + "learning_rate": 1.9401252150459478e-05, + "loss": 0.7182, + "step": 157 + }, + { + "epoch": 0.42, + "learning_rate": 1.939149756655909e-05, + "loss": 0.7161, + "step": 158 + }, + { + "epoch": 0.42, + "learning_rate": 1.9381666656903068e-05, + "loss": 0.716, + "step": 159 + }, + { + "epoch": 0.42, + "learning_rate": 1.9371759501388327e-05, + "loss": 0.7063, + "step": 160 + }, + { + "epoch": 0.42, + "learning_rate": 1.9361776180531428e-05, + "loss": 0.7126, + "step": 161 + }, + { + "epoch": 0.43, + "learning_rate": 1.935171677546794e-05, + "loss": 0.7113, + "step": 162 + }, + { + "epoch": 0.43, + "learning_rate": 1.934158136795178e-05, + "loss": 0.6949, + "step": 163 + }, + { + "epoch": 0.43, + "learning_rate": 1.933137004035454e-05, + "loss": 0.7086, + "step": 164 + }, + { + "epoch": 0.43, + "learning_rate": 1.9321082875664834e-05, + "loss": 0.7074, + "step": 165 + }, + { + "epoch": 0.44, + "learning_rate": 1.93107199574876e-05, + "loss": 0.7127, + "step": 166 + }, + { + "epoch": 0.44, + "learning_rate": 1.9300281370043433e-05, + "loss": 0.7118, + "step": 167 + }, + { + "epoch": 0.44, + "learning_rate": 1.9289767198167918e-05, + "loss": 0.7087, + "step": 168 + }, + { + "epoch": 0.45, + "learning_rate": 1.92791775273109e-05, + "loss": 0.7049, + "step": 169 + }, + { + "epoch": 0.45, + "learning_rate": 1.9268512443535826e-05, + "loss": 0.7015, + "step": 170 + }, + { + "epoch": 0.45, + "learning_rate": 1.9257772033519032e-05, + "loss": 0.7113, + "step": 171 + }, + { + "epoch": 0.45, + "learning_rate": 1.9246956384549035e-05, + "loss": 0.705, + "step": 172 + }, + { + "epoch": 0.46, + "learning_rate": 1.923606558452583e-05, + "loss": 0.7125, + "step": 173 + }, + { + "epoch": 0.46, + "learning_rate": 1.9225099721960175e-05, + "loss": 0.7083, + "step": 174 + }, + { + "epoch": 0.46, + "learning_rate": 1.921405888597286e-05, + "loss": 0.7069, + "step": 175 + }, + { + "epoch": 0.46, + "learning_rate": 1.9202943166294004e-05, + "loss": 0.7102, + "step": 176 + }, + { + "epoch": 0.47, + "learning_rate": 1.919175265326231e-05, + "loss": 0.7041, + "step": 177 + }, + { + "epoch": 0.47, + "learning_rate": 1.918048743782433e-05, + "loss": 0.7044, + "step": 178 + }, + { + "epoch": 0.47, + "learning_rate": 1.9169147611533737e-05, + "loss": 0.7013, + "step": 179 + }, + { + "epoch": 0.47, + "learning_rate": 1.9157733266550577e-05, + "loss": 0.709, + "step": 180 + }, + { + "epoch": 0.48, + "learning_rate": 1.914624449564051e-05, + "loss": 0.7059, + "step": 181 + }, + { + "epoch": 0.48, + "learning_rate": 1.9134681392174065e-05, + "loss": 0.6993, + "step": 182 + }, + { + "epoch": 0.48, + "learning_rate": 1.9123044050125892e-05, + "loss": 0.7117, + "step": 183 + }, + { + "epoch": 0.49, + "learning_rate": 1.9111332564073967e-05, + "loss": 0.7069, + "step": 184 + }, + { + "epoch": 0.49, + "learning_rate": 1.909954702919886e-05, + "loss": 0.7033, + "step": 185 + }, + { + "epoch": 0.49, + "learning_rate": 1.908768754128293e-05, + "loss": 0.7019, + "step": 186 + }, + { + "epoch": 0.49, + "learning_rate": 1.9075754196709574e-05, + "loss": 0.6988, + "step": 187 + }, + { + "epoch": 0.5, + "learning_rate": 1.906374709246242e-05, + "loss": 0.6959, + "step": 188 + }, + { + "epoch": 0.5, + "learning_rate": 1.905166632612455e-05, + "loss": 0.7012, + "step": 189 + }, + { + "epoch": 0.5, + "learning_rate": 1.9039511995877717e-05, + "loss": 0.7018, + "step": 190 + }, + { + "epoch": 0.5, + "learning_rate": 1.902728420050152e-05, + "loss": 0.7105, + "step": 191 + }, + { + "epoch": 0.51, + "learning_rate": 1.9014983039372633e-05, + "loss": 0.6964, + "step": 192 + }, + { + "epoch": 0.51, + "learning_rate": 1.900260861246397e-05, + "loss": 0.7082, + "step": 193 + }, + { + "epoch": 0.51, + "learning_rate": 1.8990161020343888e-05, + "loss": 0.7029, + "step": 194 + }, + { + "epoch": 0.51, + "learning_rate": 1.8977640364175367e-05, + "loss": 0.7039, + "step": 195 + }, + { + "epoch": 0.52, + "learning_rate": 1.8965046745715184e-05, + "loss": 0.6978, + "step": 196 + }, + { + "epoch": 0.52, + "learning_rate": 1.89523802673131e-05, + "loss": 0.7056, + "step": 197 + }, + { + "epoch": 0.52, + "learning_rate": 1.8939641031910997e-05, + "loss": 0.7023, + "step": 198 + }, + { + "epoch": 0.52, + "learning_rate": 1.8926829143042075e-05, + "loss": 0.7012, + "step": 199 + }, + { + "epoch": 0.53, + "learning_rate": 1.8913944704829996e-05, + "loss": 0.7058, + "step": 200 + }, + { + "epoch": 0.53, + "learning_rate": 1.8900987821988038e-05, + "loss": 0.6921, + "step": 201 + }, + { + "epoch": 0.53, + "learning_rate": 1.8887958599818238e-05, + "loss": 0.7128, + "step": 202 + }, + { + "epoch": 0.54, + "learning_rate": 1.887485714421055e-05, + "loss": 0.7057, + "step": 203 + }, + { + "epoch": 0.54, + "learning_rate": 1.886168356164198e-05, + "loss": 0.7052, + "step": 204 + }, + { + "epoch": 0.54, + "learning_rate": 1.8848437959175703e-05, + "loss": 0.6959, + "step": 205 + }, + { + "epoch": 0.54, + "learning_rate": 1.883512044446023e-05, + "loss": 0.7086, + "step": 206 + }, + { + "epoch": 0.55, + "learning_rate": 1.8821731125728493e-05, + "loss": 0.7021, + "step": 207 + }, + { + "epoch": 0.55, + "learning_rate": 1.880827011179699e-05, + "loss": 0.704, + "step": 208 + }, + { + "epoch": 0.55, + "learning_rate": 1.879473751206489e-05, + "loss": 0.704, + "step": 209 + }, + { + "epoch": 0.55, + "learning_rate": 1.878113343651316e-05, + "loss": 0.6995, + "step": 210 + }, + { + "epoch": 0.56, + "learning_rate": 1.876745799570364e-05, + "loss": 0.6994, + "step": 211 + }, + { + "epoch": 0.56, + "learning_rate": 1.875371130077818e-05, + "loss": 0.6939, + "step": 212 + }, + { + "epoch": 0.56, + "learning_rate": 1.873989346345771e-05, + "loss": 0.705, + "step": 213 + }, + { + "epoch": 0.56, + "learning_rate": 1.8726004596041348e-05, + "loss": 0.6989, + "step": 214 + }, + { + "epoch": 0.57, + "learning_rate": 1.871204481140548e-05, + "loss": 0.6957, + "step": 215 + }, + { + "epoch": 0.57, + "learning_rate": 1.869801422300284e-05, + "loss": 0.7077, + "step": 216 + }, + { + "epoch": 0.57, + "learning_rate": 1.8683912944861606e-05, + "loss": 0.7022, + "step": 217 + }, + { + "epoch": 0.57, + "learning_rate": 1.8669741091584435e-05, + "loss": 0.706, + "step": 218 + }, + { + "epoch": 0.58, + "learning_rate": 1.865549877834758e-05, + "loss": 0.7012, + "step": 219 + }, + { + "epoch": 0.58, + "learning_rate": 1.8641186120899918e-05, + "loss": 0.6916, + "step": 220 + }, + { + "epoch": 0.58, + "learning_rate": 1.8626803235562025e-05, + "loss": 0.705, + "step": 221 + }, + { + "epoch": 0.59, + "learning_rate": 1.8612350239225226e-05, + "loss": 0.6956, + "step": 222 + }, + { + "epoch": 0.59, + "learning_rate": 1.859782724935064e-05, + "loss": 0.7007, + "step": 223 + }, + { + "epoch": 0.59, + "learning_rate": 1.8583234383968246e-05, + "loss": 0.6974, + "step": 224 + }, + { + "epoch": 0.59, + "learning_rate": 1.8568571761675893e-05, + "loss": 0.6861, + "step": 225 + }, + { + "epoch": 0.6, + "learning_rate": 1.8553839501638365e-05, + "loss": 0.6959, + "step": 226 + }, + { + "epoch": 0.6, + "learning_rate": 1.8539037723586387e-05, + "loss": 0.6989, + "step": 227 + }, + { + "epoch": 0.6, + "learning_rate": 1.8524166547815677e-05, + "loss": 0.6944, + "step": 228 + }, + { + "epoch": 0.6, + "learning_rate": 1.850922609518595e-05, + "loss": 0.7017, + "step": 229 + }, + { + "epoch": 0.61, + "learning_rate": 1.8494216487119944e-05, + "loss": 0.7053, + "step": 230 + }, + { + "epoch": 0.61, + "learning_rate": 1.8479137845602426e-05, + "loss": 0.7007, + "step": 231 + }, + { + "epoch": 0.61, + "learning_rate": 1.8463990293179212e-05, + "loss": 0.7029, + "step": 232 + }, + { + "epoch": 0.61, + "learning_rate": 1.8448773952956164e-05, + "loss": 0.6971, + "step": 233 + }, + { + "epoch": 0.62, + "learning_rate": 1.843348894859818e-05, + "loss": 0.7081, + "step": 234 + }, + { + "epoch": 0.62, + "learning_rate": 1.8418135404328218e-05, + "loss": 0.7018, + "step": 235 + }, + { + "epoch": 0.62, + "learning_rate": 1.840271344492625e-05, + "loss": 0.7, + "step": 236 + }, + { + "epoch": 0.62, + "learning_rate": 1.8387223195728276e-05, + "loss": 0.6941, + "step": 237 + }, + { + "epoch": 0.63, + "learning_rate": 1.8371664782625287e-05, + "loss": 0.6997, + "step": 238 + }, + { + "epoch": 0.63, + "learning_rate": 1.8356038332062258e-05, + "loss": 0.6958, + "step": 239 + }, + { + "epoch": 0.63, + "learning_rate": 1.8340343971037106e-05, + "loss": 0.7004, + "step": 240 + }, + { + "epoch": 0.64, + "learning_rate": 1.8324581827099665e-05, + "loss": 0.6995, + "step": 241 + }, + { + "epoch": 0.64, + "learning_rate": 1.8308752028350652e-05, + "loss": 0.6985, + "step": 242 + }, + { + "epoch": 0.64, + "learning_rate": 1.829285470344062e-05, + "loss": 0.694, + "step": 243 + }, + { + "epoch": 0.64, + "learning_rate": 1.827688998156891e-05, + "loss": 0.6908, + "step": 244 + }, + { + "epoch": 0.65, + "learning_rate": 1.826085799248261e-05, + "loss": 0.6981, + "step": 245 + }, + { + "epoch": 0.65, + "learning_rate": 1.8244758866475498e-05, + "loss": 0.6971, + "step": 246 + }, + { + "epoch": 0.65, + "learning_rate": 1.8228592734386983e-05, + "loss": 0.6951, + "step": 247 + }, + { + "epoch": 0.65, + "learning_rate": 1.821235972760103e-05, + "loss": 0.6943, + "step": 248 + }, + { + "epoch": 0.66, + "learning_rate": 1.8196059978045117e-05, + "loss": 0.689, + "step": 249 + }, + { + "epoch": 0.66, + "learning_rate": 1.817969361818913e-05, + "loss": 0.6857, + "step": 250 + }, + { + "epoch": 0.66, + "learning_rate": 1.8163260781044317e-05, + "loss": 0.6972, + "step": 251 + }, + { + "epoch": 0.66, + "learning_rate": 1.8146761600162193e-05, + "loss": 0.7069, + "step": 252 + }, + { + "epoch": 0.67, + "learning_rate": 1.8130196209633455e-05, + "loss": 0.7136, + "step": 253 + }, + { + "epoch": 0.67, + "learning_rate": 1.811356474408689e-05, + "loss": 0.6976, + "step": 254 + }, + { + "epoch": 0.67, + "learning_rate": 1.809686733868829e-05, + "loss": 0.6875, + "step": 255 + }, + { + "epoch": 0.67, + "learning_rate": 1.8080104129139342e-05, + "loss": 0.6995, + "step": 256 + }, + { + "epoch": 0.68, + "learning_rate": 1.806327525167653e-05, + "loss": 0.6928, + "step": 257 + }, + { + "epoch": 0.68, + "learning_rate": 1.8046380843070035e-05, + "loss": 0.698, + "step": 258 + }, + { + "epoch": 0.68, + "learning_rate": 1.8029421040622614e-05, + "loss": 0.6931, + "step": 259 + }, + { + "epoch": 0.69, + "learning_rate": 1.8012395982168486e-05, + "loss": 0.6952, + "step": 260 + }, + { + "epoch": 0.69, + "learning_rate": 1.799530580607221e-05, + "loss": 0.6957, + "step": 261 + }, + { + "epoch": 0.69, + "learning_rate": 1.797815065122757e-05, + "loss": 0.6944, + "step": 262 + }, + { + "epoch": 0.69, + "learning_rate": 1.796093065705644e-05, + "loss": 0.6885, + "step": 263 + }, + { + "epoch": 0.7, + "learning_rate": 1.794364596350764e-05, + "loss": 0.6992, + "step": 264 + }, + { + "epoch": 0.7, + "learning_rate": 1.7926296711055818e-05, + "loss": 0.693, + "step": 265 + }, + { + "epoch": 0.7, + "learning_rate": 1.79088830407003e-05, + "loss": 0.6928, + "step": 266 + }, + { + "epoch": 0.7, + "learning_rate": 1.789140509396394e-05, + "loss": 0.6988, + "step": 267 + }, + { + "epoch": 0.71, + "learning_rate": 1.787386301289197e-05, + "loss": 0.6903, + "step": 268 + }, + { + "epoch": 0.71, + "learning_rate": 1.785625694005086e-05, + "loss": 0.6915, + "step": 269 + }, + { + "epoch": 0.71, + "learning_rate": 1.7838587018527135e-05, + "loss": 0.7003, + "step": 270 + }, + { + "epoch": 0.71, + "learning_rate": 1.782085339192624e-05, + "loss": 0.6888, + "step": 271 + }, + { + "epoch": 0.72, + "learning_rate": 1.780305620437134e-05, + "loss": 0.6816, + "step": 272 + }, + { + "epoch": 0.72, + "learning_rate": 1.778519560050219e-05, + "loss": 0.6891, + "step": 273 + }, + { + "epoch": 0.72, + "learning_rate": 1.7767271725473913e-05, + "loss": 0.6891, + "step": 274 + }, + { + "epoch": 0.72, + "learning_rate": 1.774928472495586e-05, + "loss": 0.6921, + "step": 275 + }, + { + "epoch": 0.73, + "learning_rate": 1.77312347451304e-05, + "loss": 0.6933, + "step": 276 + }, + { + "epoch": 0.73, + "learning_rate": 1.7713121932691755e-05, + "loss": 0.6944, + "step": 277 + }, + { + "epoch": 0.73, + "learning_rate": 1.769494643484478e-05, + "loss": 0.6853, + "step": 278 + }, + { + "epoch": 0.74, + "learning_rate": 1.7676708399303784e-05, + "loss": 0.691, + "step": 279 + }, + { + "epoch": 0.74, + "learning_rate": 1.765840797429134e-05, + "loss": 0.6983, + "step": 280 + }, + { + "epoch": 0.74, + "learning_rate": 1.764004530853705e-05, + "loss": 0.6988, + "step": 281 + }, + { + "epoch": 0.74, + "learning_rate": 1.7621620551276366e-05, + "loss": 0.6955, + "step": 282 + }, + { + "epoch": 0.75, + "learning_rate": 1.7603133852249357e-05, + "loss": 0.6907, + "step": 283 + }, + { + "epoch": 0.75, + "learning_rate": 1.75845853616995e-05, + "loss": 0.6917, + "step": 284 + }, + { + "epoch": 0.75, + "learning_rate": 1.7565975230372473e-05, + "loss": 0.6904, + "step": 285 + }, + { + "epoch": 0.75, + "learning_rate": 1.754730360951489e-05, + "loss": 0.6834, + "step": 286 + }, + { + "epoch": 0.76, + "learning_rate": 1.7528570650873115e-05, + "loss": 0.6916, + "step": 287 + }, + { + "epoch": 0.76, + "learning_rate": 1.7509776506692006e-05, + "loss": 0.6912, + "step": 288 + }, + { + "epoch": 0.76, + "learning_rate": 1.749092132971369e-05, + "loss": 0.6935, + "step": 289 + }, + { + "epoch": 0.76, + "learning_rate": 1.7472005273176306e-05, + "loss": 0.6893, + "step": 290 + }, + { + "epoch": 0.77, + "learning_rate": 1.7453028490812764e-05, + "loss": 0.6958, + "step": 291 + }, + { + "epoch": 0.77, + "learning_rate": 1.743399113684951e-05, + "loss": 0.6945, + "step": 292 + }, + { + "epoch": 0.77, + "learning_rate": 1.7414893366005263e-05, + "loss": 0.6931, + "step": 293 + }, + { + "epoch": 0.78, + "learning_rate": 1.7395735333489745e-05, + "loss": 0.6858, + "step": 294 + }, + { + "epoch": 0.78, + "learning_rate": 1.737651719500244e-05, + "loss": 0.6841, + "step": 295 + }, + { + "epoch": 0.78, + "learning_rate": 1.735723910673132e-05, + "loss": 0.6978, + "step": 296 + }, + { + "epoch": 0.78, + "learning_rate": 1.733790122535157e-05, + "loss": 0.6892, + "step": 297 + }, + { + "epoch": 0.79, + "learning_rate": 1.7318503708024326e-05, + "loss": 0.6828, + "step": 298 + }, + { + "epoch": 0.79, + "learning_rate": 1.7299046712395394e-05, + "loss": 0.6853, + "step": 299 + }, + { + "epoch": 0.79, + "learning_rate": 1.7279530396593956e-05, + "loss": 0.6845, + "step": 300 + }, + { + "epoch": 0.79, + "learning_rate": 1.725995491923131e-05, + "loss": 0.6894, + "step": 301 + }, + { + "epoch": 0.8, + "learning_rate": 1.7240320439399557e-05, + "loss": 0.6862, + "step": 302 + }, + { + "epoch": 0.8, + "learning_rate": 1.7220627116670314e-05, + "loss": 0.6892, + "step": 303 + }, + { + "epoch": 0.8, + "learning_rate": 1.7200875111093434e-05, + "loss": 0.6922, + "step": 304 + }, + { + "epoch": 0.8, + "learning_rate": 1.718106458319568e-05, + "loss": 0.6884, + "step": 305 + }, + { + "epoch": 0.81, + "learning_rate": 1.7161195693979444e-05, + "loss": 0.69, + "step": 306 + }, + { + "epoch": 0.81, + "learning_rate": 1.7141268604921414e-05, + "loss": 0.6882, + "step": 307 + }, + { + "epoch": 0.81, + "learning_rate": 1.7121283477971285e-05, + "loss": 0.6909, + "step": 308 + }, + { + "epoch": 0.81, + "learning_rate": 1.7101240475550427e-05, + "loss": 0.6874, + "step": 309 + }, + { + "epoch": 0.82, + "learning_rate": 1.7081139760550573e-05, + "loss": 0.6929, + "step": 310 + }, + { + "epoch": 0.82, + "learning_rate": 1.706098149633249e-05, + "loss": 0.6924, + "step": 311 + }, + { + "epoch": 0.82, + "learning_rate": 1.704076584672466e-05, + "loss": 0.6808, + "step": 312 + }, + { + "epoch": 0.83, + "learning_rate": 1.702049297602193e-05, + "loss": 0.6874, + "step": 313 + }, + { + "epoch": 0.83, + "learning_rate": 1.7000163048984202e-05, + "loss": 0.7009, + "step": 314 + }, + { + "epoch": 0.83, + "learning_rate": 1.6979776230835076e-05, + "loss": 0.68, + "step": 315 + }, + { + "epoch": 0.83, + "learning_rate": 1.6959332687260514e-05, + "loss": 0.6794, + "step": 316 + }, + { + "epoch": 0.84, + "learning_rate": 1.6938832584407494e-05, + "loss": 0.6944, + "step": 317 + }, + { + "epoch": 0.84, + "learning_rate": 1.6918276088882648e-05, + "loss": 0.6841, + "step": 318 + }, + { + "epoch": 0.84, + "learning_rate": 1.689766336775093e-05, + "loss": 0.6845, + "step": 319 + }, + { + "epoch": 0.84, + "learning_rate": 1.6876994588534234e-05, + "loss": 0.6865, + "step": 320 + }, + { + "epoch": 0.85, + "learning_rate": 1.6856269919210056e-05, + "loss": 0.6806, + "step": 321 + }, + { + "epoch": 0.85, + "learning_rate": 1.6835489528210107e-05, + "loss": 0.6858, + "step": 322 + }, + { + "epoch": 0.85, + "learning_rate": 1.6814653584418966e-05, + "loss": 0.683, + "step": 323 + }, + { + "epoch": 0.85, + "learning_rate": 1.6793762257172675e-05, + "loss": 0.6849, + "step": 324 + }, + { + "epoch": 0.86, + "learning_rate": 1.6772815716257414e-05, + "loss": 0.6901, + "step": 325 + }, + { + "epoch": 0.86, + "learning_rate": 1.675181413190806e-05, + "loss": 0.6878, + "step": 326 + }, + { + "epoch": 0.86, + "learning_rate": 1.6730757674806858e-05, + "loss": 0.6908, + "step": 327 + }, + { + "epoch": 0.86, + "learning_rate": 1.6709646516081992e-05, + "loss": 0.6954, + "step": 328 + }, + { + "epoch": 0.87, + "learning_rate": 1.6688480827306224e-05, + "loss": 0.6902, + "step": 329 + }, + { + "epoch": 0.87, + "learning_rate": 1.6667260780495483e-05, + "loss": 0.6877, + "step": 330 + }, + { + "epoch": 0.87, + "learning_rate": 1.664598654810748e-05, + "loss": 0.6837, + "step": 331 + }, + { + "epoch": 0.88, + "learning_rate": 1.662465830304028e-05, + "loss": 0.6842, + "step": 332 + }, + { + "epoch": 0.88, + "learning_rate": 1.6603276218630932e-05, + "loss": 0.6865, + "step": 333 + }, + { + "epoch": 0.88, + "learning_rate": 1.658184046865404e-05, + "loss": 0.6817, + "step": 334 + }, + { + "epoch": 0.88, + "learning_rate": 1.656035122732035e-05, + "loss": 0.6841, + "step": 335 + }, + { + "epoch": 0.89, + "learning_rate": 1.6538808669275335e-05, + "loss": 0.6803, + "step": 336 + }, + { + "epoch": 0.89, + "learning_rate": 1.6517212969597793e-05, + "loss": 0.6757, + "step": 337 + }, + { + "epoch": 0.89, + "learning_rate": 1.6495564303798392e-05, + "loss": 0.6739, + "step": 338 + }, + { + "epoch": 0.89, + "learning_rate": 1.647386284781828e-05, + "loss": 0.6898, + "step": 339 + }, + { + "epoch": 0.9, + "learning_rate": 1.645210877802762e-05, + "loss": 0.6958, + "step": 340 + }, + { + "epoch": 0.9, + "learning_rate": 1.6430302271224178e-05, + "loss": 0.6931, + "step": 341 + }, + { + "epoch": 0.9, + "learning_rate": 1.6408443504631897e-05, + "loss": 0.6943, + "step": 342 + }, + { + "epoch": 0.9, + "learning_rate": 1.6386532655899418e-05, + "loss": 0.6907, + "step": 343 + }, + { + "epoch": 0.91, + "learning_rate": 1.6364569903098672e-05, + "loss": 0.683, + "step": 344 + }, + { + "epoch": 0.91, + "learning_rate": 1.634255542472342e-05, + "loss": 0.6897, + "step": 345 + }, + { + "epoch": 0.91, + "learning_rate": 1.63204893996878e-05, + "loss": 0.6767, + "step": 346 + }, + { + "epoch": 0.91, + "learning_rate": 1.6298372007324873e-05, + "loss": 0.6837, + "step": 347 + }, + { + "epoch": 0.92, + "learning_rate": 1.6276203427385175e-05, + "loss": 0.6713, + "step": 348 + }, + { + "epoch": 0.92, + "learning_rate": 1.6253983840035243e-05, + "loss": 0.6828, + "step": 349 + }, + { + "epoch": 0.92, + "learning_rate": 1.6231713425856156e-05, + "loss": 0.6803, + "step": 350 + }, + { + "epoch": 0.93, + "learning_rate": 1.620939236584208e-05, + "loss": 0.6834, + "step": 351 + }, + { + "epoch": 0.93, + "learning_rate": 1.6187020841398773e-05, + "loss": 0.6787, + "step": 352 + }, + { + "epoch": 0.93, + "learning_rate": 1.6164599034342122e-05, + "loss": 0.6888, + "step": 353 + }, + { + "epoch": 0.93, + "learning_rate": 1.6142127126896682e-05, + "loss": 0.6882, + "step": 354 + }, + { + "epoch": 0.94, + "learning_rate": 1.6119605301694156e-05, + "loss": 0.6835, + "step": 355 + }, + { + "epoch": 0.94, + "learning_rate": 1.609703374177196e-05, + "loss": 0.688, + "step": 356 + }, + { + "epoch": 0.94, + "learning_rate": 1.6074412630571685e-05, + "loss": 0.6756, + "step": 357 + }, + { + "epoch": 0.94, + "learning_rate": 1.6051742151937655e-05, + "loss": 0.6828, + "step": 358 + }, + { + "epoch": 0.95, + "learning_rate": 1.6029022490115383e-05, + "loss": 0.6785, + "step": 359 + }, + { + "epoch": 0.95, + "learning_rate": 1.6006253829750125e-05, + "loss": 0.6883, + "step": 360 + }, + { + "epoch": 0.95, + "learning_rate": 1.5983436355885333e-05, + "loss": 0.6832, + "step": 361 + }, + { + "epoch": 0.95, + "learning_rate": 1.5960570253961185e-05, + "loss": 0.6873, + "step": 362 + }, + { + "epoch": 0.96, + "learning_rate": 1.593765570981306e-05, + "loss": 0.679, + "step": 363 + }, + { + "epoch": 0.96, + "learning_rate": 1.591469290967002e-05, + "loss": 0.6892, + "step": 364 + }, + { + "epoch": 0.96, + "learning_rate": 1.589168204015334e-05, + "loss": 0.6864, + "step": 365 + }, + { + "epoch": 0.96, + "learning_rate": 1.586862328827493e-05, + "loss": 0.6865, + "step": 366 + }, + { + "epoch": 0.97, + "learning_rate": 1.584551684143586e-05, + "loss": 0.6868, + "step": 367 + }, + { + "epoch": 0.97, + "learning_rate": 1.5822362887424817e-05, + "loss": 0.6811, + "step": 368 + }, + { + "epoch": 0.97, + "learning_rate": 1.579916161441658e-05, + "loss": 0.6845, + "step": 369 + }, + { + "epoch": 0.98, + "learning_rate": 1.5775913210970518e-05, + "loss": 0.6893, + "step": 370 + }, + { + "epoch": 0.98, + "learning_rate": 1.5752617866029005e-05, + "loss": 0.6874, + "step": 371 + }, + { + "epoch": 0.98, + "learning_rate": 1.5729275768915924e-05, + "loss": 0.685, + "step": 372 + }, + { + "epoch": 0.98, + "learning_rate": 1.5705887109335124e-05, + "loss": 0.6774, + "step": 373 + }, + { + "epoch": 0.99, + "learning_rate": 1.568245207736887e-05, + "loss": 0.6784, + "step": 374 + }, + { + "epoch": 0.99, + "learning_rate": 1.5658970863476298e-05, + "loss": 0.6826, + "step": 375 + }, + { + "epoch": 0.99, + "learning_rate": 1.563544365849187e-05, + "loss": 0.6794, + "step": 376 + }, + { + "epoch": 0.99, + "learning_rate": 1.5611870653623826e-05, + "loss": 0.6755, + "step": 377 + }, + { + "epoch": 1.0, + "learning_rate": 1.558825204045262e-05, + "loss": 0.6755, + "step": 378 + }, + { + "epoch": 1.0, + "learning_rate": 1.5564588010929375e-05, + "loss": 0.6837, + "step": 379 + }, + { + "epoch": 1.0, + "learning_rate": 1.5540878757374326e-05, + "loss": 0.6542, + "step": 380 + }, + { + "epoch": 1.0, + "learning_rate": 1.551712447247523e-05, + "loss": 0.6466, + "step": 381 + }, + { + "epoch": 1.01, + "learning_rate": 1.5493325349285824e-05, + "loss": 0.6388, + "step": 382 + }, + { + "epoch": 1.01, + "learning_rate": 1.5469481581224274e-05, + "loss": 0.64, + "step": 383 + }, + { + "epoch": 1.01, + "learning_rate": 1.544559336207154e-05, + "loss": 0.6419, + "step": 384 + }, + { + "epoch": 1.01, + "learning_rate": 1.5421660885969875e-05, + "loss": 0.6334, + "step": 385 + }, + { + "epoch": 1.02, + "learning_rate": 1.53976843474212e-05, + "loss": 0.6315, + "step": 386 + }, + { + "epoch": 1.02, + "learning_rate": 1.5373663941285536e-05, + "loss": 0.6332, + "step": 387 + }, + { + "epoch": 1.02, + "learning_rate": 1.534959986277942e-05, + "loss": 0.6447, + "step": 388 + }, + { + "epoch": 1.03, + "learning_rate": 1.5325492307474314e-05, + "loss": 0.6364, + "step": 389 + }, + { + "epoch": 1.03, + "learning_rate": 1.530134147129504e-05, + "loss": 0.6338, + "step": 390 + }, + { + "epoch": 1.03, + "learning_rate": 1.5277147550518156e-05, + "loss": 0.6409, + "step": 391 + }, + { + "epoch": 1.03, + "learning_rate": 1.5252910741770364e-05, + "loss": 0.6452, + "step": 392 + }, + { + "epoch": 1.04, + "learning_rate": 1.522863124202694e-05, + "loss": 0.6306, + "step": 393 + }, + { + "epoch": 1.04, + "learning_rate": 1.5204309248610103e-05, + "loss": 0.637, + "step": 394 + }, + { + "epoch": 1.04, + "learning_rate": 1.5179944959187423e-05, + "loss": 0.6401, + "step": 395 + }, + { + "epoch": 1.04, + "learning_rate": 1.515553857177022e-05, + "loss": 0.6346, + "step": 396 + }, + { + "epoch": 1.05, + "learning_rate": 1.5131090284711942e-05, + "loss": 0.6388, + "step": 397 + }, + { + "epoch": 1.05, + "learning_rate": 1.5106600296706568e-05, + "loss": 0.6294, + "step": 398 + }, + { + "epoch": 1.05, + "learning_rate": 1.508206880678698e-05, + "loss": 0.6393, + "step": 399 + }, + { + "epoch": 1.05, + "learning_rate": 1.5057496014323354e-05, + "loss": 0.6315, + "step": 400 + }, + { + "epoch": 1.06, + "learning_rate": 1.503288211902153e-05, + "loss": 0.6358, + "step": 401 + }, + { + "epoch": 1.06, + "learning_rate": 1.5008227320921402e-05, + "loss": 0.6313, + "step": 402 + }, + { + "epoch": 1.06, + "learning_rate": 1.4983531820395287e-05, + "loss": 0.6384, + "step": 403 + }, + { + "epoch": 1.07, + "learning_rate": 1.4958795818146287e-05, + "loss": 0.6383, + "step": 404 + }, + { + "epoch": 1.07, + "learning_rate": 1.4934019515206675e-05, + "loss": 0.6337, + "step": 405 + }, + { + "epoch": 1.07, + "learning_rate": 1.4909203112936244e-05, + "loss": 0.6336, + "step": 406 + }, + { + "epoch": 1.07, + "learning_rate": 1.4884346813020685e-05, + "loss": 0.6376, + "step": 407 + }, + { + "epoch": 1.08, + "learning_rate": 1.4859450817469938e-05, + "loss": 0.6446, + "step": 408 + }, + { + "epoch": 1.08, + "learning_rate": 1.4834515328616555e-05, + "loss": 0.6298, + "step": 409 + }, + { + "epoch": 1.08, + "learning_rate": 1.4809540549114059e-05, + "loss": 0.6257, + "step": 410 + }, + { + "epoch": 1.08, + "learning_rate": 1.4784526681935282e-05, + "loss": 0.643, + "step": 411 + }, + { + "epoch": 1.09, + "learning_rate": 1.4759473930370738e-05, + "loss": 0.6342, + "step": 412 + }, + { + "epoch": 1.09, + "learning_rate": 1.4734382498026946e-05, + "loss": 0.6334, + "step": 413 + }, + { + "epoch": 1.09, + "learning_rate": 1.4709252588824805e-05, + "loss": 0.633, + "step": 414 + }, + { + "epoch": 1.09, + "learning_rate": 1.4684084406997903e-05, + "loss": 0.6379, + "step": 415 + }, + { + "epoch": 1.1, + "learning_rate": 1.4658878157090879e-05, + "loss": 0.632, + "step": 416 + }, + { + "epoch": 1.1, + "learning_rate": 1.4633634043957767e-05, + "loss": 0.6392, + "step": 417 + }, + { + "epoch": 1.1, + "learning_rate": 1.46083522727603e-05, + "loss": 0.6397, + "step": 418 + }, + { + "epoch": 1.1, + "learning_rate": 1.4583033048966273e-05, + "loss": 0.6319, + "step": 419 + }, + { + "epoch": 1.11, + "learning_rate": 1.4557676578347868e-05, + "loss": 0.6351, + "step": 420 + }, + { + "epoch": 1.11, + "learning_rate": 1.4532283066979967e-05, + "loss": 0.627, + "step": 421 + }, + { + "epoch": 1.11, + "learning_rate": 1.4506852721238485e-05, + "loss": 0.6438, + "step": 422 + }, + { + "epoch": 1.12, + "learning_rate": 1.4481385747798705e-05, + "loss": 0.636, + "step": 423 + }, + { + "epoch": 1.12, + "learning_rate": 1.4455882353633576e-05, + "loss": 0.6398, + "step": 424 + }, + { + "epoch": 1.12, + "learning_rate": 1.4430342746012049e-05, + "loss": 0.6342, + "step": 425 + }, + { + "epoch": 1.12, + "learning_rate": 1.4404767132497386e-05, + "loss": 0.6419, + "step": 426 + }, + { + "epoch": 1.13, + "learning_rate": 1.4379155720945464e-05, + "loss": 0.6369, + "step": 427 + }, + { + "epoch": 1.13, + "learning_rate": 1.4353508719503114e-05, + "loss": 0.6307, + "step": 428 + }, + { + "epoch": 1.13, + "learning_rate": 1.4327826336606383e-05, + "loss": 0.6397, + "step": 429 + }, + { + "epoch": 1.13, + "learning_rate": 1.4302108780978889e-05, + "loss": 0.6307, + "step": 430 + }, + { + "epoch": 1.14, + "learning_rate": 1.4276356261630096e-05, + "loss": 0.6448, + "step": 431 + }, + { + "epoch": 1.14, + "learning_rate": 1.425056898785362e-05, + "loss": 0.6325, + "step": 432 + }, + { + "epoch": 1.14, + "learning_rate": 1.4224747169225527e-05, + "loss": 0.6488, + "step": 433 + }, + { + "epoch": 1.14, + "learning_rate": 1.4198891015602648e-05, + "loss": 0.636, + "step": 434 + }, + { + "epoch": 1.15, + "learning_rate": 1.4173000737120839e-05, + "loss": 0.6423, + "step": 435 + }, + { + "epoch": 1.15, + "learning_rate": 1.4147076544193303e-05, + "loss": 0.6419, + "step": 436 + }, + { + "epoch": 1.15, + "learning_rate": 1.4121118647508872e-05, + "loss": 0.6431, + "step": 437 + }, + { + "epoch": 1.15, + "learning_rate": 1.4095127258030283e-05, + "loss": 0.6334, + "step": 438 + }, + { + "epoch": 1.16, + "learning_rate": 1.406910258699248e-05, + "loss": 0.6304, + "step": 439 + }, + { + "epoch": 1.16, + "learning_rate": 1.4043044845900889e-05, + "loss": 0.6421, + "step": 440 + }, + { + "epoch": 1.16, + "learning_rate": 1.4016954246529697e-05, + "loss": 0.6346, + "step": 441 + }, + { + "epoch": 1.17, + "learning_rate": 1.3990831000920135e-05, + "loss": 0.6299, + "step": 442 + }, + { + "epoch": 1.17, + "learning_rate": 1.3964675321378756e-05, + "loss": 0.6327, + "step": 443 + }, + { + "epoch": 1.17, + "learning_rate": 1.3938487420475703e-05, + "loss": 0.631, + "step": 444 + }, + { + "epoch": 1.17, + "learning_rate": 1.3912267511042994e-05, + "loss": 0.637, + "step": 445 + }, + { + "epoch": 1.18, + "learning_rate": 1.3886015806172774e-05, + "loss": 0.6501, + "step": 446 + }, + { + "epoch": 1.18, + "learning_rate": 1.3859732519215596e-05, + "loss": 0.6364, + "step": 447 + }, + { + "epoch": 1.18, + "learning_rate": 1.3833417863778689e-05, + "loss": 0.6433, + "step": 448 + }, + { + "epoch": 1.18, + "learning_rate": 1.380707205372421e-05, + "loss": 0.6383, + "step": 449 + }, + { + "epoch": 1.19, + "learning_rate": 1.378069530316752e-05, + "loss": 0.6411, + "step": 450 + }, + { + "epoch": 1.19, + "learning_rate": 1.3754287826475428e-05, + "loss": 0.6436, + "step": 451 + }, + { + "epoch": 1.19, + "learning_rate": 1.3727849838264472e-05, + "loss": 0.6341, + "step": 452 + }, + { + "epoch": 1.19, + "learning_rate": 1.3701381553399147e-05, + "loss": 0.6356, + "step": 453 + }, + { + "epoch": 1.2, + "learning_rate": 1.3674883186990174e-05, + "loss": 0.6323, + "step": 454 + }, + { + "epoch": 1.2, + "learning_rate": 1.3648354954392758e-05, + "loss": 0.6309, + "step": 455 + }, + { + "epoch": 1.2, + "learning_rate": 1.3621797071204823e-05, + "loss": 0.6328, + "step": 456 + }, + { + "epoch": 1.2, + "learning_rate": 1.3595209753265266e-05, + "loss": 0.6282, + "step": 457 + }, + { + "epoch": 1.21, + "learning_rate": 1.3568593216652215e-05, + "loss": 0.6341, + "step": 458 + }, + { + "epoch": 1.21, + "learning_rate": 1.3541947677681246e-05, + "loss": 0.6337, + "step": 459 + }, + { + "epoch": 1.21, + "learning_rate": 1.3515273352903649e-05, + "loss": 0.637, + "step": 460 + }, + { + "epoch": 1.22, + "learning_rate": 1.3488570459104656e-05, + "loss": 0.6486, + "step": 461 + }, + { + "epoch": 1.22, + "learning_rate": 1.3461839213301684e-05, + "loss": 0.6347, + "step": 462 + }, + { + "epoch": 1.22, + "learning_rate": 1.3435079832742577e-05, + "loss": 0.6356, + "step": 463 + }, + { + "epoch": 1.22, + "learning_rate": 1.3408292534903817e-05, + "loss": 0.6386, + "step": 464 + }, + { + "epoch": 1.23, + "learning_rate": 1.338147753748879e-05, + "loss": 0.6397, + "step": 465 + }, + { + "epoch": 1.23, + "learning_rate": 1.3354635058425986e-05, + "loss": 0.6224, + "step": 466 + }, + { + "epoch": 1.23, + "learning_rate": 1.3327765315867253e-05, + "loss": 0.6332, + "step": 467 + }, + { + "epoch": 1.23, + "learning_rate": 1.3300868528186001e-05, + "loss": 0.6453, + "step": 468 + }, + { + "epoch": 1.24, + "learning_rate": 1.3273944913975452e-05, + "loss": 0.6288, + "step": 469 + }, + { + "epoch": 1.24, + "learning_rate": 1.3246994692046837e-05, + "loss": 0.6338, + "step": 470 + }, + { + "epoch": 1.24, + "learning_rate": 1.3220018081427637e-05, + "loss": 0.6377, + "step": 471 + }, + { + "epoch": 1.24, + "learning_rate": 1.31930153013598e-05, + "loss": 0.6313, + "step": 472 + }, + { + "epoch": 1.25, + "learning_rate": 1.3165986571297953e-05, + "loss": 0.6414, + "step": 473 + }, + { + "epoch": 1.25, + "learning_rate": 1.3138932110907616e-05, + "loss": 0.6339, + "step": 474 + }, + { + "epoch": 1.25, + "learning_rate": 1.3111852140063435e-05, + "loss": 0.634, + "step": 475 + }, + { + "epoch": 1.25, + "learning_rate": 1.3084746878847367e-05, + "loss": 0.6386, + "step": 476 + }, + { + "epoch": 1.26, + "learning_rate": 1.305761654754692e-05, + "loss": 0.6353, + "step": 477 + }, + { + "epoch": 1.26, + "learning_rate": 1.303046136665334e-05, + "loss": 0.6424, + "step": 478 + }, + { + "epoch": 1.26, + "learning_rate": 1.3003281556859837e-05, + "loss": 0.6363, + "step": 479 + }, + { + "epoch": 1.27, + "learning_rate": 1.2976077339059774e-05, + "loss": 0.6336, + "step": 480 + }, + { + "epoch": 1.27, + "learning_rate": 1.2948848934344885e-05, + "loss": 0.6336, + "step": 481 + }, + { + "epoch": 1.27, + "learning_rate": 1.2921596564003479e-05, + "loss": 0.6357, + "step": 482 + }, + { + "epoch": 1.27, + "learning_rate": 1.2894320449518624e-05, + "loss": 0.6393, + "step": 483 + }, + { + "epoch": 1.28, + "learning_rate": 1.286702081256637e-05, + "loss": 0.6414, + "step": 484 + }, + { + "epoch": 1.28, + "learning_rate": 1.283969787501393e-05, + "loss": 0.6235, + "step": 485 + }, + { + "epoch": 1.28, + "learning_rate": 1.281235185891789e-05, + "loss": 0.6428, + "step": 486 + }, + { + "epoch": 1.28, + "learning_rate": 1.2784982986522399e-05, + "loss": 0.6328, + "step": 487 + }, + { + "epoch": 1.29, + "learning_rate": 1.2757591480257342e-05, + "loss": 0.6327, + "step": 488 + }, + { + "epoch": 1.29, + "learning_rate": 1.2730177562736583e-05, + "loss": 0.638, + "step": 489 + }, + { + "epoch": 1.29, + "learning_rate": 1.27027414567561e-05, + "loss": 0.6353, + "step": 490 + }, + { + "epoch": 1.29, + "learning_rate": 1.2675283385292212e-05, + "loss": 0.6416, + "step": 491 + }, + { + "epoch": 1.3, + "learning_rate": 1.2647803571499744e-05, + "loss": 0.6411, + "step": 492 + }, + { + "epoch": 1.3, + "learning_rate": 1.2620302238710238e-05, + "loss": 0.6223, + "step": 493 + }, + { + "epoch": 1.3, + "learning_rate": 1.2592779610430111e-05, + "loss": 0.6301, + "step": 494 + }, + { + "epoch": 1.3, + "learning_rate": 1.2565235910338852e-05, + "loss": 0.6355, + "step": 495 + }, + { + "epoch": 1.31, + "learning_rate": 1.2537671362287207e-05, + "loss": 0.6344, + "step": 496 + }, + { + "epoch": 1.31, + "learning_rate": 1.2510086190295358e-05, + "loss": 0.6314, + "step": 497 + }, + { + "epoch": 1.31, + "learning_rate": 1.2482480618551092e-05, + "loss": 0.6365, + "step": 498 + }, + { + "epoch": 1.32, + "learning_rate": 1.2454854871407993e-05, + "loss": 0.6308, + "step": 499 + }, + { + "epoch": 1.32, + "learning_rate": 1.2427209173383612e-05, + "loss": 0.644, + "step": 500 + }, + { + "epoch": 1.32, + "learning_rate": 1.239954374915764e-05, + "loss": 0.6347, + "step": 501 + }, + { + "epoch": 1.32, + "learning_rate": 1.2371858823570085e-05, + "loss": 0.6298, + "step": 502 + }, + { + "epoch": 1.33, + "learning_rate": 1.234415462161945e-05, + "loss": 0.6334, + "step": 503 + }, + { + "epoch": 1.33, + "learning_rate": 1.2316431368460902e-05, + "loss": 0.6423, + "step": 504 + }, + { + "epoch": 1.33, + "learning_rate": 1.2288689289404424e-05, + "loss": 0.6354, + "step": 505 + }, + { + "epoch": 1.33, + "learning_rate": 1.226092860991301e-05, + "loss": 0.6385, + "step": 506 + }, + { + "epoch": 1.34, + "learning_rate": 1.2233149555600827e-05, + "loss": 0.6399, + "step": 507 + }, + { + "epoch": 1.34, + "learning_rate": 1.2205352352231364e-05, + "loss": 0.6458, + "step": 508 + }, + { + "epoch": 1.34, + "learning_rate": 1.2177537225715615e-05, + "loss": 0.6471, + "step": 509 + }, + { + "epoch": 1.34, + "learning_rate": 1.2149704402110243e-05, + "loss": 0.6308, + "step": 510 + }, + { + "epoch": 1.35, + "learning_rate": 1.2121854107615726e-05, + "loss": 0.6326, + "step": 511 + }, + { + "epoch": 1.35, + "learning_rate": 1.2093986568574537e-05, + "loss": 0.6301, + "step": 512 + }, + { + "epoch": 1.35, + "learning_rate": 1.2066102011469295e-05, + "loss": 0.6346, + "step": 513 + }, + { + "epoch": 1.36, + "learning_rate": 1.2038200662920933e-05, + "loss": 0.6359, + "step": 514 + }, + { + "epoch": 1.36, + "learning_rate": 1.2010282749686839e-05, + "loss": 0.6345, + "step": 515 + }, + { + "epoch": 1.36, + "learning_rate": 1.1982348498659031e-05, + "loss": 0.6402, + "step": 516 + }, + { + "epoch": 1.36, + "learning_rate": 1.1954398136862308e-05, + "loss": 0.6271, + "step": 517 + }, + { + "epoch": 1.37, + "learning_rate": 1.1926431891452397e-05, + "loss": 0.6343, + "step": 518 + }, + { + "epoch": 1.37, + "learning_rate": 1.1898449989714116e-05, + "loss": 0.6421, + "step": 519 + }, + { + "epoch": 1.37, + "learning_rate": 1.1870452659059522e-05, + "loss": 0.631, + "step": 520 + }, + { + "epoch": 1.37, + "learning_rate": 1.184244012702607e-05, + "loss": 0.6372, + "step": 521 + }, + { + "epoch": 1.38, + "learning_rate": 1.1814412621274751e-05, + "loss": 0.6321, + "step": 522 + }, + { + "epoch": 1.38, + "learning_rate": 1.1786370369588257e-05, + "loss": 0.6342, + "step": 523 + }, + { + "epoch": 1.38, + "learning_rate": 1.175831359986911e-05, + "loss": 0.6354, + "step": 524 + }, + { + "epoch": 1.38, + "learning_rate": 1.1730242540137835e-05, + "loss": 0.6354, + "step": 525 + }, + { + "epoch": 1.39, + "learning_rate": 1.1702157418531084e-05, + "loss": 0.6297, + "step": 526 + }, + { + "epoch": 1.39, + "learning_rate": 1.1674058463299798e-05, + "loss": 0.6406, + "step": 527 + }, + { + "epoch": 1.39, + "learning_rate": 1.164594590280734e-05, + "loss": 0.6342, + "step": 528 + }, + { + "epoch": 1.39, + "learning_rate": 1.161781996552765e-05, + "loss": 0.6469, + "step": 529 + }, + { + "epoch": 1.4, + "learning_rate": 1.1589680880043372e-05, + "loss": 0.6359, + "step": 530 + }, + { + "epoch": 1.4, + "learning_rate": 1.1561528875044026e-05, + "loss": 0.6318, + "step": 531 + }, + { + "epoch": 1.4, + "learning_rate": 1.1533364179324109e-05, + "loss": 0.6356, + "step": 532 + }, + { + "epoch": 1.41, + "learning_rate": 1.150518702178127e-05, + "loss": 0.6323, + "step": 533 + }, + { + "epoch": 1.41, + "learning_rate": 1.147699763141444e-05, + "loss": 0.6305, + "step": 534 + }, + { + "epoch": 1.41, + "learning_rate": 1.1448796237321949e-05, + "loss": 0.6319, + "step": 535 + }, + { + "epoch": 1.41, + "learning_rate": 1.14205830686997e-05, + "loss": 0.634, + "step": 536 + }, + { + "epoch": 1.42, + "learning_rate": 1.1392358354839286e-05, + "loss": 0.6322, + "step": 537 + }, + { + "epoch": 1.42, + "learning_rate": 1.1364122325126123e-05, + "loss": 0.6366, + "step": 538 + }, + { + "epoch": 1.42, + "learning_rate": 1.1335875209037598e-05, + "loss": 0.6439, + "step": 539 + }, + { + "epoch": 1.42, + "learning_rate": 1.1307617236141195e-05, + "loss": 0.6427, + "step": 540 + }, + { + "epoch": 1.43, + "learning_rate": 1.1279348636092634e-05, + "loss": 0.637, + "step": 541 + }, + { + "epoch": 1.43, + "learning_rate": 1.125106963863401e-05, + "loss": 0.6414, + "step": 542 + }, + { + "epoch": 1.43, + "learning_rate": 1.1222780473591902e-05, + "loss": 0.6347, + "step": 543 + }, + { + "epoch": 1.43, + "learning_rate": 1.1194481370875531e-05, + "loss": 0.637, + "step": 544 + }, + { + "epoch": 1.44, + "learning_rate": 1.1166172560474894e-05, + "loss": 0.6332, + "step": 545 + }, + { + "epoch": 1.44, + "learning_rate": 1.1137854272458866e-05, + "loss": 0.6368, + "step": 546 + }, + { + "epoch": 1.44, + "learning_rate": 1.110952673697335e-05, + "loss": 0.631, + "step": 547 + }, + { + "epoch": 1.44, + "learning_rate": 1.1081190184239418e-05, + "loss": 0.6326, + "step": 548 + }, + { + "epoch": 1.45, + "learning_rate": 1.1052844844551416e-05, + "loss": 0.631, + "step": 549 + }, + { + "epoch": 1.45, + "learning_rate": 1.1024490948275096e-05, + "loss": 0.6357, + "step": 550 + }, + { + "epoch": 1.45, + "learning_rate": 1.0996128725845764e-05, + "loss": 0.6268, + "step": 551 + }, + { + "epoch": 1.46, + "learning_rate": 1.096775840776639e-05, + "loss": 0.6288, + "step": 552 + }, + { + "epoch": 1.46, + "learning_rate": 1.0939380224605727e-05, + "loss": 0.6353, + "step": 553 + }, + { + "epoch": 1.46, + "learning_rate": 1.0910994406996463e-05, + "loss": 0.6324, + "step": 554 + }, + { + "epoch": 1.46, + "learning_rate": 1.0882601185633326e-05, + "loss": 0.6333, + "step": 555 + }, + { + "epoch": 1.47, + "learning_rate": 1.0854200791271215e-05, + "loss": 0.6289, + "step": 556 + }, + { + "epoch": 1.47, + "learning_rate": 1.0825793454723325e-05, + "loss": 0.6334, + "step": 557 + }, + { + "epoch": 1.47, + "learning_rate": 1.079737940685927e-05, + "loss": 0.6312, + "step": 558 + }, + { + "epoch": 1.47, + "learning_rate": 1.076895887860321e-05, + "loss": 0.636, + "step": 559 + }, + { + "epoch": 1.48, + "learning_rate": 1.0740532100931969e-05, + "loss": 0.6359, + "step": 560 + }, + { + "epoch": 1.48, + "learning_rate": 1.0712099304873161e-05, + "loss": 0.6316, + "step": 561 + }, + { + "epoch": 1.48, + "learning_rate": 1.0683660721503318e-05, + "loss": 0.6366, + "step": 562 + }, + { + "epoch": 1.48, + "learning_rate": 1.0655216581945997e-05, + "loss": 0.625, + "step": 563 + }, + { + "epoch": 1.49, + "learning_rate": 1.0626767117369916e-05, + "loss": 0.6315, + "step": 564 + }, + { + "epoch": 1.49, + "learning_rate": 1.0598312558987072e-05, + "loss": 0.6363, + "step": 565 + }, + { + "epoch": 1.49, + "learning_rate": 1.0569853138050856e-05, + "loss": 0.6294, + "step": 566 + }, + { + "epoch": 1.49, + "learning_rate": 1.0541389085854177e-05, + "loss": 0.6408, + "step": 567 + }, + { + "epoch": 1.5, + "learning_rate": 1.0512920633727583e-05, + "loss": 0.6291, + "step": 568 + }, + { + "epoch": 1.5, + "learning_rate": 1.048444801303739e-05, + "loss": 0.6323, + "step": 569 + }, + { + "epoch": 1.5, + "learning_rate": 1.0455971455183775e-05, + "loss": 0.6327, + "step": 570 + }, + { + "epoch": 1.51, + "learning_rate": 1.0427491191598926e-05, + "loss": 0.6443, + "step": 571 + }, + { + "epoch": 1.51, + "learning_rate": 1.0399007453745147e-05, + "loss": 0.6345, + "step": 572 + }, + { + "epoch": 1.51, + "learning_rate": 1.037052047311297e-05, + "loss": 0.6331, + "step": 573 + }, + { + "epoch": 1.51, + "learning_rate": 1.034203048121929e-05, + "loss": 0.6264, + "step": 574 + }, + { + "epoch": 1.52, + "learning_rate": 1.031353770960547e-05, + "loss": 0.6227, + "step": 575 + }, + { + "epoch": 1.52, + "learning_rate": 1.0285042389835466e-05, + "loss": 0.6286, + "step": 576 + }, + { + "epoch": 1.52, + "learning_rate": 1.0256544753493945e-05, + "loss": 0.64, + "step": 577 + }, + { + "epoch": 1.52, + "learning_rate": 1.022804503218439e-05, + "loss": 0.6298, + "step": 578 + }, + { + "epoch": 1.53, + "learning_rate": 1.0199543457527247e-05, + "loss": 0.6365, + "step": 579 + }, + { + "epoch": 1.53, + "learning_rate": 1.0171040261158012e-05, + "loss": 0.6306, + "step": 580 + }, + { + "epoch": 1.53, + "learning_rate": 1.014253567472536e-05, + "loss": 0.6356, + "step": 581 + }, + { + "epoch": 1.53, + "learning_rate": 1.011402992988927e-05, + "loss": 0.6403, + "step": 582 + }, + { + "epoch": 1.54, + "learning_rate": 1.0085523258319131e-05, + "loss": 0.6386, + "step": 583 + }, + { + "epoch": 1.54, + "learning_rate": 1.0057015891691866e-05, + "loss": 0.6288, + "step": 584 + }, + { + "epoch": 1.54, + "learning_rate": 1.0028508061690044e-05, + "loss": 0.6324, + "step": 585 + }, + { + "epoch": 1.54, + "learning_rate": 1e-05, + "loss": 0.6263, + "step": 586 + }, + { + "epoch": 1.55, + "learning_rate": 9.971491938309963e-06, + "loss": 0.6396, + "step": 587 + }, + { + "epoch": 1.55, + "learning_rate": 9.942984108308137e-06, + "loss": 0.6314, + "step": 588 + }, + { + "epoch": 1.55, + "learning_rate": 9.914476741680872e-06, + "loss": 0.6322, + "step": 589 + }, + { + "epoch": 1.56, + "learning_rate": 9.885970070110733e-06, + "loss": 0.6333, + "step": 590 + }, + { + "epoch": 1.56, + "learning_rate": 9.857464325274643e-06, + "loss": 0.6218, + "step": 591 + }, + { + "epoch": 1.56, + "learning_rate": 9.82895973884199e-06, + "loss": 0.6325, + "step": 592 + }, + { + "epoch": 1.56, + "learning_rate": 9.800456542472754e-06, + "loss": 0.6351, + "step": 593 + }, + { + "epoch": 1.57, + "learning_rate": 9.77195496781561e-06, + "loss": 0.6367, + "step": 594 + }, + { + "epoch": 1.57, + "learning_rate": 9.743455246506059e-06, + "loss": 0.6309, + "step": 595 + }, + { + "epoch": 1.57, + "learning_rate": 9.714957610164534e-06, + "loss": 0.6351, + "step": 596 + }, + { + "epoch": 1.57, + "learning_rate": 9.686462290394533e-06, + "loss": 0.6241, + "step": 597 + }, + { + "epoch": 1.58, + "learning_rate": 9.657969518780714e-06, + "loss": 0.6286, + "step": 598 + }, + { + "epoch": 1.58, + "learning_rate": 9.629479526887032e-06, + "loss": 0.6325, + "step": 599 + }, + { + "epoch": 1.58, + "learning_rate": 9.60099254625486e-06, + "loss": 0.6348, + "step": 600 + }, + { + "epoch": 1.58, + "learning_rate": 9.572508808401078e-06, + "loss": 0.6393, + "step": 601 + }, + { + "epoch": 1.59, + "learning_rate": 9.544028544816229e-06, + "loss": 0.6467, + "step": 602 + }, + { + "epoch": 1.59, + "learning_rate": 9.515551986962614e-06, + "loss": 0.628, + "step": 603 + }, + { + "epoch": 1.59, + "learning_rate": 9.487079366272419e-06, + "loss": 0.6306, + "step": 604 + }, + { + "epoch": 1.59, + "learning_rate": 9.458610914145826e-06, + "loss": 0.6315, + "step": 605 + }, + { + "epoch": 1.6, + "learning_rate": 9.430146861949147e-06, + "loss": 0.6213, + "step": 606 + }, + { + "epoch": 1.6, + "learning_rate": 9.401687441012928e-06, + "loss": 0.6356, + "step": 607 + }, + { + "epoch": 1.6, + "learning_rate": 9.373232882630087e-06, + "loss": 0.6304, + "step": 608 + }, + { + "epoch": 1.61, + "learning_rate": 9.344783418054005e-06, + "loss": 0.6303, + "step": 609 + }, + { + "epoch": 1.61, + "learning_rate": 9.316339278496685e-06, + "loss": 0.6314, + "step": 610 + }, + { + "epoch": 1.61, + "learning_rate": 9.287900695126844e-06, + "loss": 0.6289, + "step": 611 + }, + { + "epoch": 1.61, + "learning_rate": 9.259467899068034e-06, + "loss": 0.6357, + "step": 612 + }, + { + "epoch": 1.62, + "learning_rate": 9.231041121396795e-06, + "loss": 0.6249, + "step": 613 + }, + { + "epoch": 1.62, + "learning_rate": 9.202620593140732e-06, + "loss": 0.6372, + "step": 614 + }, + { + "epoch": 1.62, + "learning_rate": 9.174206545276678e-06, + "loss": 0.6335, + "step": 615 + }, + { + "epoch": 1.62, + "learning_rate": 9.145799208728785e-06, + "loss": 0.6356, + "step": 616 + }, + { + "epoch": 1.63, + "learning_rate": 9.117398814366677e-06, + "loss": 0.6287, + "step": 617 + }, + { + "epoch": 1.63, + "learning_rate": 9.089005593003539e-06, + "loss": 0.6316, + "step": 618 + }, + { + "epoch": 1.63, + "learning_rate": 9.060619775394276e-06, + "loss": 0.6224, + "step": 619 + }, + { + "epoch": 1.63, + "learning_rate": 9.032241592233612e-06, + "loss": 0.6287, + "step": 620 + }, + { + "epoch": 1.64, + "learning_rate": 9.003871274154237e-06, + "loss": 0.6362, + "step": 621 + }, + { + "epoch": 1.64, + "learning_rate": 8.975509051724908e-06, + "loss": 0.6266, + "step": 622 + }, + { + "epoch": 1.64, + "learning_rate": 8.947155155448588e-06, + "loss": 0.634, + "step": 623 + }, + { + "epoch": 1.65, + "learning_rate": 8.918809815760585e-06, + "loss": 0.6176, + "step": 624 + }, + { + "epoch": 1.65, + "learning_rate": 8.890473263026653e-06, + "loss": 0.6284, + "step": 625 + }, + { + "epoch": 1.65, + "learning_rate": 8.862145727541141e-06, + "loss": 0.634, + "step": 626 + }, + { + "epoch": 1.65, + "learning_rate": 8.833827439525109e-06, + "loss": 0.6292, + "step": 627 + }, + { + "epoch": 1.66, + "learning_rate": 8.805518629124472e-06, + "loss": 0.6383, + "step": 628 + }, + { + "epoch": 1.66, + "learning_rate": 8.777219526408103e-06, + "loss": 0.63, + "step": 629 + }, + { + "epoch": 1.66, + "learning_rate": 8.748930361365994e-06, + "loss": 0.6262, + "step": 630 + }, + { + "epoch": 1.66, + "learning_rate": 8.720651363907364e-06, + "loss": 0.6378, + "step": 631 + }, + { + "epoch": 1.67, + "learning_rate": 8.692382763858807e-06, + "loss": 0.629, + "step": 632 + }, + { + "epoch": 1.67, + "learning_rate": 8.664124790962407e-06, + "loss": 0.6281, + "step": 633 + }, + { + "epoch": 1.67, + "learning_rate": 8.63587767487388e-06, + "loss": 0.6281, + "step": 634 + }, + { + "epoch": 1.67, + "learning_rate": 8.607641645160721e-06, + "loss": 0.6182, + "step": 635 + }, + { + "epoch": 1.68, + "learning_rate": 8.579416931300303e-06, + "loss": 0.6332, + "step": 636 + }, + { + "epoch": 1.68, + "learning_rate": 8.551203762678056e-06, + "loss": 0.6259, + "step": 637 + }, + { + "epoch": 1.68, + "learning_rate": 8.523002368585564e-06, + "loss": 0.6334, + "step": 638 + }, + { + "epoch": 1.68, + "learning_rate": 8.494812978218732e-06, + "loss": 0.6295, + "step": 639 + }, + { + "epoch": 1.69, + "learning_rate": 8.466635820675891e-06, + "loss": 0.6311, + "step": 640 + }, + { + "epoch": 1.69, + "learning_rate": 8.438471124955979e-06, + "loss": 0.6278, + "step": 641 + }, + { + "epoch": 1.69, + "learning_rate": 8.410319119956626e-06, + "loss": 0.6304, + "step": 642 + }, + { + "epoch": 1.7, + "learning_rate": 8.382180034472353e-06, + "loss": 0.6339, + "step": 643 + }, + { + "epoch": 1.7, + "learning_rate": 8.35405409719266e-06, + "loss": 0.627, + "step": 644 + }, + { + "epoch": 1.7, + "learning_rate": 8.325941536700206e-06, + "loss": 0.6267, + "step": 645 + }, + { + "epoch": 1.7, + "learning_rate": 8.29784258146892e-06, + "loss": 0.629, + "step": 646 + }, + { + "epoch": 1.71, + "learning_rate": 8.269757459862169e-06, + "loss": 0.6298, + "step": 647 + }, + { + "epoch": 1.71, + "learning_rate": 8.241686400130895e-06, + "loss": 0.6335, + "step": 648 + }, + { + "epoch": 1.71, + "learning_rate": 8.213629630411747e-06, + "loss": 0.6317, + "step": 649 + }, + { + "epoch": 1.71, + "learning_rate": 8.18558737872525e-06, + "loss": 0.6291, + "step": 650 + }, + { + "epoch": 1.72, + "learning_rate": 8.157559872973932e-06, + "loss": 0.6358, + "step": 651 + }, + { + "epoch": 1.72, + "learning_rate": 8.129547340940481e-06, + "loss": 0.6232, + "step": 652 + }, + { + "epoch": 1.72, + "learning_rate": 8.101550010285887e-06, + "loss": 0.641, + "step": 653 + }, + { + "epoch": 1.72, + "learning_rate": 8.073568108547607e-06, + "loss": 0.6215, + "step": 654 + }, + { + "epoch": 1.73, + "learning_rate": 8.045601863137694e-06, + "loss": 0.6351, + "step": 655 + }, + { + "epoch": 1.73, + "learning_rate": 8.017651501340972e-06, + "loss": 0.6285, + "step": 656 + }, + { + "epoch": 1.73, + "learning_rate": 7.989717250313165e-06, + "loss": 0.6257, + "step": 657 + }, + { + "epoch": 1.73, + "learning_rate": 7.96179933707907e-06, + "loss": 0.6302, + "step": 658 + }, + { + "epoch": 1.74, + "learning_rate": 7.93389798853071e-06, + "loss": 0.6277, + "step": 659 + }, + { + "epoch": 1.74, + "learning_rate": 7.906013431425468e-06, + "loss": 0.6335, + "step": 660 + }, + { + "epoch": 1.74, + "learning_rate": 7.878145892384279e-06, + "loss": 0.6337, + "step": 661 + }, + { + "epoch": 1.75, + "learning_rate": 7.85029559788976e-06, + "loss": 0.6214, + "step": 662 + }, + { + "epoch": 1.75, + "learning_rate": 7.822462774284389e-06, + "loss": 0.6291, + "step": 663 + }, + { + "epoch": 1.75, + "learning_rate": 7.794647647768636e-06, + "loss": 0.6274, + "step": 664 + }, + { + "epoch": 1.75, + "learning_rate": 7.766850444399176e-06, + "loss": 0.6276, + "step": 665 + }, + { + "epoch": 1.76, + "learning_rate": 7.73907139008699e-06, + "loss": 0.6274, + "step": 666 + }, + { + "epoch": 1.76, + "learning_rate": 7.711310710595578e-06, + "loss": 0.634, + "step": 667 + }, + { + "epoch": 1.76, + "learning_rate": 7.6835686315391e-06, + "loss": 0.6195, + "step": 668 + }, + { + "epoch": 1.76, + "learning_rate": 7.655845378380551e-06, + "loss": 0.6304, + "step": 669 + }, + { + "epoch": 1.77, + "learning_rate": 7.6281411764299185e-06, + "loss": 0.6386, + "step": 670 + }, + { + "epoch": 1.77, + "learning_rate": 7.600456250842364e-06, + "loss": 0.6229, + "step": 671 + }, + { + "epoch": 1.77, + "learning_rate": 7.5727908266163945e-06, + "loss": 0.6372, + "step": 672 + }, + { + "epoch": 1.77, + "learning_rate": 7.545145128592009e-06, + "loss": 0.6296, + "step": 673 + }, + { + "epoch": 1.78, + "learning_rate": 7.51751938144891e-06, + "loss": 0.6333, + "step": 674 + }, + { + "epoch": 1.78, + "learning_rate": 7.489913809704643e-06, + "loss": 0.6277, + "step": 675 + }, + { + "epoch": 1.78, + "learning_rate": 7.4623286377127944e-06, + "loss": 0.6227, + "step": 676 + }, + { + "epoch": 1.78, + "learning_rate": 7.434764089661151e-06, + "loss": 0.6252, + "step": 677 + }, + { + "epoch": 1.79, + "learning_rate": 7.407220389569892e-06, + "loss": 0.6177, + "step": 678 + }, + { + "epoch": 1.79, + "learning_rate": 7.379697761289763e-06, + "loss": 0.6261, + "step": 679 + }, + { + "epoch": 1.79, + "learning_rate": 7.3521964285002575e-06, + "loss": 0.6314, + "step": 680 + }, + { + "epoch": 1.8, + "learning_rate": 7.324716614707794e-06, + "loss": 0.6305, + "step": 681 + }, + { + "epoch": 1.8, + "learning_rate": 7.297258543243904e-06, + "loss": 0.6387, + "step": 682 + }, + { + "epoch": 1.8, + "learning_rate": 7.269822437263423e-06, + "loss": 0.6266, + "step": 683 + }, + { + "epoch": 1.8, + "learning_rate": 7.242408519742659e-06, + "loss": 0.6189, + "step": 684 + }, + { + "epoch": 1.81, + "learning_rate": 7.215017013477607e-06, + "loss": 0.6222, + "step": 685 + }, + { + "epoch": 1.81, + "learning_rate": 7.1876481410821085e-06, + "loss": 0.6349, + "step": 686 + }, + { + "epoch": 1.81, + "learning_rate": 7.160302124986073e-06, + "loss": 0.6283, + "step": 687 + }, + { + "epoch": 1.81, + "learning_rate": 7.132979187433633e-06, + "loss": 0.6301, + "step": 688 + }, + { + "epoch": 1.82, + "learning_rate": 7.105679550481379e-06, + "loss": 0.6264, + "step": 689 + }, + { + "epoch": 1.82, + "learning_rate": 7.078403435996524e-06, + "loss": 0.6242, + "step": 690 + }, + { + "epoch": 1.82, + "learning_rate": 7.0511510656551175e-06, + "loss": 0.633, + "step": 691 + }, + { + "epoch": 1.82, + "learning_rate": 7.023922660940231e-06, + "loss": 0.6291, + "step": 692 + }, + { + "epoch": 1.83, + "learning_rate": 6.9967184431401665e-06, + "loss": 0.6246, + "step": 693 + }, + { + "epoch": 1.83, + "learning_rate": 6.969538633346663e-06, + "loss": 0.6246, + "step": 694 + }, + { + "epoch": 1.83, + "learning_rate": 6.942383452453083e-06, + "loss": 0.6287, + "step": 695 + }, + { + "epoch": 1.83, + "learning_rate": 6.915253121152637e-06, + "loss": 0.6306, + "step": 696 + }, + { + "epoch": 1.84, + "learning_rate": 6.888147859936569e-06, + "loss": 0.6267, + "step": 697 + }, + { + "epoch": 1.84, + "learning_rate": 6.861067889092385e-06, + "loss": 0.6255, + "step": 698 + }, + { + "epoch": 1.84, + "learning_rate": 6.834013428702049e-06, + "loss": 0.63, + "step": 699 + }, + { + "epoch": 1.85, + "learning_rate": 6.806984698640202e-06, + "loss": 0.6164, + "step": 700 + }, + { + "epoch": 1.85, + "learning_rate": 6.779981918572364e-06, + "loss": 0.6191, + "step": 701 + }, + { + "epoch": 1.85, + "learning_rate": 6.7530053079531664e-06, + "loss": 0.6285, + "step": 702 + }, + { + "epoch": 1.85, + "learning_rate": 6.72605508602455e-06, + "loss": 0.6368, + "step": 703 + }, + { + "epoch": 1.86, + "learning_rate": 6.699131471814001e-06, + "loss": 0.625, + "step": 704 + }, + { + "epoch": 1.86, + "learning_rate": 6.6722346841327515e-06, + "loss": 0.6193, + "step": 705 + }, + { + "epoch": 1.86, + "learning_rate": 6.645364941574015e-06, + "loss": 0.6276, + "step": 706 + }, + { + "epoch": 1.86, + "learning_rate": 6.6185224625112155e-06, + "loss": 0.6204, + "step": 707 + }, + { + "epoch": 1.87, + "learning_rate": 6.591707465096185e-06, + "loss": 0.6261, + "step": 708 + }, + { + "epoch": 1.87, + "learning_rate": 6.564920167257427e-06, + "loss": 0.6251, + "step": 709 + }, + { + "epoch": 1.87, + "learning_rate": 6.538160786698315e-06, + "loss": 0.6256, + "step": 710 + }, + { + "epoch": 1.87, + "learning_rate": 6.511429540895349e-06, + "loss": 0.6257, + "step": 711 + }, + { + "epoch": 1.88, + "learning_rate": 6.484726647096354e-06, + "loss": 0.6203, + "step": 712 + }, + { + "epoch": 1.88, + "learning_rate": 6.458052322318758e-06, + "loss": 0.6246, + "step": 713 + }, + { + "epoch": 1.88, + "learning_rate": 6.431406783347786e-06, + "loss": 0.6301, + "step": 714 + }, + { + "epoch": 1.88, + "learning_rate": 6.4047902467347355e-06, + "loss": 0.6182, + "step": 715 + }, + { + "epoch": 1.89, + "learning_rate": 6.378202928795183e-06, + "loss": 0.6363, + "step": 716 + }, + { + "epoch": 1.89, + "learning_rate": 6.3516450456072465e-06, + "loss": 0.6292, + "step": 717 + }, + { + "epoch": 1.89, + "learning_rate": 6.325116813009832e-06, + "loss": 0.6302, + "step": 718 + }, + { + "epoch": 1.9, + "learning_rate": 6.298618446600856e-06, + "loss": 0.6296, + "step": 719 + }, + { + "epoch": 1.9, + "learning_rate": 6.272150161735531e-06, + "loss": 0.6215, + "step": 720 + }, + { + "epoch": 1.9, + "learning_rate": 6.245712173524572e-06, + "loss": 0.625, + "step": 721 + }, + { + "epoch": 1.9, + "learning_rate": 6.219304696832482e-06, + "loss": 0.6324, + "step": 722 + }, + { + "epoch": 1.91, + "learning_rate": 6.1929279462757905e-06, + "loss": 0.6248, + "step": 723 + }, + { + "epoch": 1.91, + "learning_rate": 6.166582136221314e-06, + "loss": 0.6222, + "step": 724 + }, + { + "epoch": 1.91, + "learning_rate": 6.140267480784405e-06, + "loss": 0.6248, + "step": 725 + }, + { + "epoch": 1.91, + "learning_rate": 6.1139841938272284e-06, + "loss": 0.6313, + "step": 726 + }, + { + "epoch": 1.92, + "learning_rate": 6.08773248895701e-06, + "loss": 0.6238, + "step": 727 + }, + { + "epoch": 1.92, + "learning_rate": 6.061512579524298e-06, + "loss": 0.6241, + "step": 728 + }, + { + "epoch": 1.92, + "learning_rate": 6.035324678621248e-06, + "loss": 0.6257, + "step": 729 + }, + { + "epoch": 1.92, + "learning_rate": 6.009168999079867e-06, + "loss": 0.6207, + "step": 730 + }, + { + "epoch": 1.93, + "learning_rate": 5.983045753470308e-06, + "loss": 0.6371, + "step": 731 + }, + { + "epoch": 1.93, + "learning_rate": 5.9569551540991135e-06, + "loss": 0.6346, + "step": 732 + }, + { + "epoch": 1.93, + "learning_rate": 5.930897413007523e-06, + "loss": 0.6205, + "step": 733 + }, + { + "epoch": 1.94, + "learning_rate": 5.904872741969718e-06, + "loss": 0.6133, + "step": 734 + }, + { + "epoch": 1.94, + "learning_rate": 5.8788813524911324e-06, + "loss": 0.6331, + "step": 735 + }, + { + "epoch": 1.94, + "learning_rate": 5.8529234558066985e-06, + "loss": 0.6234, + "step": 736 + }, + { + "epoch": 1.94, + "learning_rate": 5.826999262879164e-06, + "loss": 0.6234, + "step": 737 + }, + { + "epoch": 1.95, + "learning_rate": 5.801108984397355e-06, + "loss": 0.6331, + "step": 738 + }, + { + "epoch": 1.95, + "learning_rate": 5.775252830774475e-06, + "loss": 0.6288, + "step": 739 + }, + { + "epoch": 1.95, + "learning_rate": 5.749431012146388e-06, + "loss": 0.6244, + "step": 740 + }, + { + "epoch": 1.95, + "learning_rate": 5.723643738369909e-06, + "loss": 0.6271, + "step": 741 + }, + { + "epoch": 1.96, + "learning_rate": 5.6978912190211145e-06, + "loss": 0.6245, + "step": 742 + }, + { + "epoch": 1.96, + "learning_rate": 5.672173663393618e-06, + "loss": 0.6277, + "step": 743 + }, + { + "epoch": 1.96, + "learning_rate": 5.646491280496893e-06, + "loss": 0.6248, + "step": 744 + }, + { + "epoch": 1.96, + "learning_rate": 5.620844279054536e-06, + "loss": 0.6283, + "step": 745 + }, + { + "epoch": 1.97, + "learning_rate": 5.595232867502619e-06, + "loss": 0.6231, + "step": 746 + }, + { + "epoch": 1.97, + "learning_rate": 5.569657253987952e-06, + "loss": 0.6283, + "step": 747 + }, + { + "epoch": 1.97, + "learning_rate": 5.544117646366425e-06, + "loss": 0.6212, + "step": 748 + }, + { + "epoch": 1.97, + "learning_rate": 5.518614252201295e-06, + "loss": 0.6199, + "step": 749 + }, + { + "epoch": 1.98, + "learning_rate": 5.493147278761517e-06, + "loss": 0.6233, + "step": 750 + }, + { + "epoch": 1.98, + "learning_rate": 5.46771693302004e-06, + "loss": 0.6112, + "step": 751 + }, + { + "epoch": 1.98, + "learning_rate": 5.442323421652136e-06, + "loss": 0.6314, + "step": 752 + }, + { + "epoch": 1.99, + "learning_rate": 5.416966951033731e-06, + "loss": 0.6314, + "step": 753 + }, + { + "epoch": 1.99, + "learning_rate": 5.391647727239706e-06, + "loss": 0.6284, + "step": 754 + }, + { + "epoch": 1.99, + "learning_rate": 5.366365956042236e-06, + "loss": 0.6279, + "step": 755 + }, + { + "epoch": 1.99, + "learning_rate": 5.341121842909119e-06, + "loss": 0.6316, + "step": 756 + }, + { + "epoch": 2.0, + "learning_rate": 5.3159155930021e-06, + "loss": 0.6229, + "step": 757 + }, + { + "epoch": 2.0, + "learning_rate": 5.290747411175195e-06, + "loss": 0.6235, + "step": 758 + }, + { + "epoch": 2.0, + "learning_rate": 5.265617501973055e-06, + "loss": 0.607, + "step": 759 + }, + { + "epoch": 2.0, + "learning_rate": 5.240526069629265e-06, + "loss": 0.5831, + "step": 760 + }, + { + "epoch": 2.01, + "learning_rate": 5.215473318064722e-06, + "loss": 0.5819, + "step": 761 + }, + { + "epoch": 2.01, + "learning_rate": 5.190459450885945e-06, + "loss": 0.5882, + "step": 762 + }, + { + "epoch": 2.01, + "learning_rate": 5.165484671383445e-06, + "loss": 0.5807, + "step": 763 + }, + { + "epoch": 2.01, + "learning_rate": 5.140549182530066e-06, + "loss": 0.5892, + "step": 764 + }, + { + "epoch": 2.02, + "learning_rate": 5.115653186979318e-06, + "loss": 0.5945, + "step": 765 + }, + { + "epoch": 2.02, + "learning_rate": 5.09079688706376e-06, + "loss": 0.5844, + "step": 766 + }, + { + "epoch": 2.02, + "learning_rate": 5.065980484793328e-06, + "loss": 0.5868, + "step": 767 + }, + { + "epoch": 2.02, + "learning_rate": 5.041204181853716e-06, + "loss": 0.578, + "step": 768 + }, + { + "epoch": 2.03, + "learning_rate": 5.016468179604712e-06, + "loss": 0.5867, + "step": 769 + }, + { + "epoch": 2.03, + "learning_rate": 4.991772679078598e-06, + "loss": 0.5787, + "step": 770 + }, + { + "epoch": 2.03, + "learning_rate": 4.96711788097847e-06, + "loss": 0.589, + "step": 771 + }, + { + "epoch": 2.04, + "learning_rate": 4.94250398567665e-06, + "loss": 0.5851, + "step": 772 + }, + { + "epoch": 2.04, + "learning_rate": 4.91793119321302e-06, + "loss": 0.5846, + "step": 773 + }, + { + "epoch": 2.04, + "learning_rate": 4.893399703293436e-06, + "loss": 0.5842, + "step": 774 + }, + { + "epoch": 2.04, + "learning_rate": 4.86890971528806e-06, + "loss": 0.5875, + "step": 775 + }, + { + "epoch": 2.05, + "learning_rate": 4.844461428229782e-06, + "loss": 0.5773, + "step": 776 + }, + { + "epoch": 2.05, + "learning_rate": 4.82005504081258e-06, + "loss": 0.5891, + "step": 777 + }, + { + "epoch": 2.05, + "learning_rate": 4.795690751389899e-06, + "loss": 0.5927, + "step": 778 + }, + { + "epoch": 2.05, + "learning_rate": 4.771368757973062e-06, + "loss": 0.5874, + "step": 779 + }, + { + "epoch": 2.06, + "learning_rate": 4.747089258229635e-06, + "loss": 0.5796, + "step": 780 + }, + { + "epoch": 2.06, + "learning_rate": 4.722852449481848e-06, + "loss": 0.5769, + "step": 781 + }, + { + "epoch": 2.06, + "learning_rate": 4.69865852870496e-06, + "loss": 0.5755, + "step": 782 + }, + { + "epoch": 2.06, + "learning_rate": 4.674507692525685e-06, + "loss": 0.5819, + "step": 783 + }, + { + "epoch": 2.07, + "learning_rate": 4.650400137220583e-06, + "loss": 0.5801, + "step": 784 + }, + { + "epoch": 2.07, + "learning_rate": 4.626336058714468e-06, + "loss": 0.578, + "step": 785 + }, + { + "epoch": 2.07, + "learning_rate": 4.6023156525788034e-06, + "loss": 0.5912, + "step": 786 + }, + { + "epoch": 2.07, + "learning_rate": 4.578339114030127e-06, + "loss": 0.5767, + "step": 787 + }, + { + "epoch": 2.08, + "learning_rate": 4.554406637928464e-06, + "loss": 0.5857, + "step": 788 + }, + { + "epoch": 2.08, + "learning_rate": 4.530518418775734e-06, + "loss": 0.5727, + "step": 789 + }, + { + "epoch": 2.08, + "learning_rate": 4.5066746507141755e-06, + "loss": 0.5783, + "step": 790 + }, + { + "epoch": 2.09, + "learning_rate": 4.482875527524774e-06, + "loss": 0.5809, + "step": 791 + }, + { + "epoch": 2.09, + "learning_rate": 4.459121242625678e-06, + "loss": 0.5822, + "step": 792 + }, + { + "epoch": 2.09, + "learning_rate": 4.435411989070624e-06, + "loss": 0.5769, + "step": 793 + }, + { + "epoch": 2.09, + "learning_rate": 4.411747959547384e-06, + "loss": 0.5782, + "step": 794 + }, + { + "epoch": 2.1, + "learning_rate": 4.388129346376177e-06, + "loss": 0.5783, + "step": 795 + }, + { + "epoch": 2.1, + "learning_rate": 4.364556341508134e-06, + "loss": 0.5786, + "step": 796 + }, + { + "epoch": 2.1, + "learning_rate": 4.341029136523701e-06, + "loss": 0.5704, + "step": 797 + }, + { + "epoch": 2.1, + "learning_rate": 4.317547922631132e-06, + "loss": 0.5818, + "step": 798 + }, + { + "epoch": 2.11, + "learning_rate": 4.2941128906648786e-06, + "loss": 0.5836, + "step": 799 + }, + { + "epoch": 2.11, + "learning_rate": 4.270724231084079e-06, + "loss": 0.5672, + "step": 800 + }, + { + "epoch": 2.11, + "learning_rate": 4.247382133971002e-06, + "loss": 0.5789, + "step": 801 + }, + { + "epoch": 2.11, + "learning_rate": 4.2240867890294845e-06, + "loss": 0.5761, + "step": 802 + }, + { + "epoch": 2.12, + "learning_rate": 4.200838385583417e-06, + "loss": 0.5927, + "step": 803 + }, + { + "epoch": 2.12, + "learning_rate": 4.177637112575185e-06, + "loss": 0.5832, + "step": 804 + }, + { + "epoch": 2.12, + "learning_rate": 4.154483158564143e-06, + "loss": 0.5871, + "step": 805 + }, + { + "epoch": 2.12, + "learning_rate": 4.13137671172507e-06, + "loss": 0.582, + "step": 806 + }, + { + "epoch": 2.13, + "learning_rate": 4.1083179598466625e-06, + "loss": 0.5769, + "step": 807 + }, + { + "epoch": 2.13, + "learning_rate": 4.085307090329978e-06, + "loss": 0.5869, + "step": 808 + }, + { + "epoch": 2.13, + "learning_rate": 4.062344290186947e-06, + "loss": 0.5821, + "step": 809 + }, + { + "epoch": 2.14, + "learning_rate": 4.039429746038818e-06, + "loss": 0.5775, + "step": 810 + }, + { + "epoch": 2.14, + "learning_rate": 4.0165636441146676e-06, + "loss": 0.5894, + "step": 811 + }, + { + "epoch": 2.14, + "learning_rate": 3.993746170249878e-06, + "loss": 0.5766, + "step": 812 + }, + { + "epoch": 2.14, + "learning_rate": 3.970977509884617e-06, + "loss": 0.5879, + "step": 813 + }, + { + "epoch": 2.15, + "learning_rate": 3.948257848062351e-06, + "loss": 0.5805, + "step": 814 + }, + { + "epoch": 2.15, + "learning_rate": 3.925587369428316e-06, + "loss": 0.5796, + "step": 815 + }, + { + "epoch": 2.15, + "learning_rate": 3.902966258228046e-06, + "loss": 0.5811, + "step": 816 + }, + { + "epoch": 2.15, + "learning_rate": 3.880394698305846e-06, + "loss": 0.5893, + "step": 817 + }, + { + "epoch": 2.16, + "learning_rate": 3.857872873103322e-06, + "loss": 0.5902, + "step": 818 + }, + { + "epoch": 2.16, + "learning_rate": 3.8354009656578775e-06, + "loss": 0.5836, + "step": 819 + }, + { + "epoch": 2.16, + "learning_rate": 3.812979158601231e-06, + "loss": 0.5802, + "step": 820 + }, + { + "epoch": 2.16, + "learning_rate": 3.7906076341579235e-06, + "loss": 0.5887, + "step": 821 + }, + { + "epoch": 2.17, + "learning_rate": 3.768286574143846e-06, + "loss": 0.5867, + "step": 822 + }, + { + "epoch": 2.17, + "learning_rate": 3.746016159964764e-06, + "loss": 0.5871, + "step": 823 + }, + { + "epoch": 2.17, + "learning_rate": 3.723796572614826e-06, + "loss": 0.5858, + "step": 824 + }, + { + "epoch": 2.17, + "learning_rate": 3.70162799267513e-06, + "loss": 0.5799, + "step": 825 + }, + { + "epoch": 2.18, + "learning_rate": 3.679510600312203e-06, + "loss": 0.5809, + "step": 826 + }, + { + "epoch": 2.18, + "learning_rate": 3.657444575276583e-06, + "loss": 0.5779, + "step": 827 + }, + { + "epoch": 2.18, + "learning_rate": 3.635430096901329e-06, + "loss": 0.5797, + "step": 828 + }, + { + "epoch": 2.19, + "learning_rate": 3.6134673441005864e-06, + "loss": 0.5832, + "step": 829 + }, + { + "epoch": 2.19, + "learning_rate": 3.591556495368106e-06, + "loss": 0.5852, + "step": 830 + }, + { + "epoch": 2.19, + "learning_rate": 3.5696977287758205e-06, + "loss": 0.5807, + "step": 831 + }, + { + "epoch": 2.19, + "learning_rate": 3.5478912219723826e-06, + "loss": 0.573, + "step": 832 + }, + { + "epoch": 2.2, + "learning_rate": 3.5261371521817247e-06, + "loss": 0.5744, + "step": 833 + }, + { + "epoch": 2.2, + "learning_rate": 3.5044356962016114e-06, + "loss": 0.589, + "step": 834 + }, + { + "epoch": 2.2, + "learning_rate": 3.4827870304022116e-06, + "loss": 0.582, + "step": 835 + }, + { + "epoch": 2.2, + "learning_rate": 3.461191330724669e-06, + "loss": 0.5777, + "step": 836 + }, + { + "epoch": 2.21, + "learning_rate": 3.4396487726796545e-06, + "loss": 0.5863, + "step": 837 + }, + { + "epoch": 2.21, + "learning_rate": 3.4181595313459613e-06, + "loss": 0.5799, + "step": 838 + }, + { + "epoch": 2.21, + "learning_rate": 3.396723781369067e-06, + "loss": 0.5741, + "step": 839 + }, + { + "epoch": 2.21, + "learning_rate": 3.375341696959722e-06, + "loss": 0.5796, + "step": 840 + }, + { + "epoch": 2.22, + "learning_rate": 3.3540134518925226e-06, + "loss": 0.5782, + "step": 841 + }, + { + "epoch": 2.22, + "learning_rate": 3.3327392195045173e-06, + "loss": 0.5842, + "step": 842 + }, + { + "epoch": 2.22, + "learning_rate": 3.311519172693778e-06, + "loss": 0.5803, + "step": 843 + }, + { + "epoch": 2.23, + "learning_rate": 3.290353483918013e-06, + "loss": 0.5796, + "step": 844 + }, + { + "epoch": 2.23, + "learning_rate": 3.269242325193147e-06, + "loss": 0.5883, + "step": 845 + }, + { + "epoch": 2.23, + "learning_rate": 3.248185868091941e-06, + "loss": 0.5852, + "step": 846 + }, + { + "epoch": 2.23, + "learning_rate": 3.2271842837425917e-06, + "loss": 0.5778, + "step": 847 + }, + { + "epoch": 2.24, + "learning_rate": 3.206237742827325e-06, + "loss": 0.5866, + "step": 848 + }, + { + "epoch": 2.24, + "learning_rate": 3.185346415581041e-06, + "loss": 0.5826, + "step": 849 + }, + { + "epoch": 2.24, + "learning_rate": 3.1645104717898946e-06, + "loss": 0.5771, + "step": 850 + }, + { + "epoch": 2.24, + "learning_rate": 3.1437300807899462e-06, + "loss": 0.5778, + "step": 851 + }, + { + "epoch": 2.25, + "learning_rate": 3.123005411465766e-06, + "loss": 0.5783, + "step": 852 + }, + { + "epoch": 2.25, + "learning_rate": 3.1023366322490733e-06, + "loss": 0.5772, + "step": 853 + }, + { + "epoch": 2.25, + "learning_rate": 3.0817239111173523e-06, + "loss": 0.5838, + "step": 854 + }, + { + "epoch": 2.25, + "learning_rate": 3.0611674155925085e-06, + "loss": 0.5853, + "step": 855 + }, + { + "epoch": 2.26, + "learning_rate": 3.0406673127394894e-06, + "loss": 0.5756, + "step": 856 + }, + { + "epoch": 2.26, + "learning_rate": 3.0202237691649263e-06, + "loss": 0.5787, + "step": 857 + }, + { + "epoch": 2.26, + "learning_rate": 2.999836951015801e-06, + "loss": 0.5849, + "step": 858 + }, + { + "epoch": 2.26, + "learning_rate": 2.9795070239780734e-06, + "loss": 0.5865, + "step": 859 + }, + { + "epoch": 2.27, + "learning_rate": 2.9592341532753455e-06, + "loss": 0.5793, + "step": 860 + }, + { + "epoch": 2.27, + "learning_rate": 2.939018503667511e-06, + "loss": 0.5851, + "step": 861 + }, + { + "epoch": 2.27, + "learning_rate": 2.91886023944943e-06, + "loss": 0.5747, + "step": 862 + }, + { + "epoch": 2.28, + "learning_rate": 2.8987595244495736e-06, + "loss": 0.5856, + "step": 863 + }, + { + "epoch": 2.28, + "learning_rate": 2.8787165220287183e-06, + "loss": 0.5763, + "step": 864 + }, + { + "epoch": 2.28, + "learning_rate": 2.8587313950785876e-06, + "loss": 0.5798, + "step": 865 + }, + { + "epoch": 2.28, + "learning_rate": 2.838804306020557e-06, + "loss": 0.5819, + "step": 866 + }, + { + "epoch": 2.29, + "learning_rate": 2.8189354168043183e-06, + "loss": 0.5862, + "step": 867 + }, + { + "epoch": 2.29, + "learning_rate": 2.7991248889065693e-06, + "loss": 0.5838, + "step": 868 + }, + { + "epoch": 2.29, + "learning_rate": 2.7793728833296906e-06, + "loss": 0.5847, + "step": 869 + }, + { + "epoch": 2.29, + "learning_rate": 2.7596795606004477e-06, + "loss": 0.5818, + "step": 870 + }, + { + "epoch": 2.3, + "learning_rate": 2.740045080768694e-06, + "loss": 0.5869, + "step": 871 + }, + { + "epoch": 2.3, + "learning_rate": 2.7204696034060464e-06, + "loss": 0.5826, + "step": 872 + }, + { + "epoch": 2.3, + "learning_rate": 2.7009532876046084e-06, + "loss": 0.5758, + "step": 873 + }, + { + "epoch": 2.3, + "learning_rate": 2.681496291975674e-06, + "loss": 0.5778, + "step": 874 + }, + { + "epoch": 2.31, + "learning_rate": 2.662098774648434e-06, + "loss": 0.5852, + "step": 875 + }, + { + "epoch": 2.31, + "learning_rate": 2.642760893268684e-06, + "loss": 0.588, + "step": 876 + }, + { + "epoch": 2.31, + "learning_rate": 2.6234828049975645e-06, + "loss": 0.5788, + "step": 877 + }, + { + "epoch": 2.31, + "learning_rate": 2.6042646665102587e-06, + "loss": 0.584, + "step": 878 + }, + { + "epoch": 2.32, + "learning_rate": 2.5851066339947397e-06, + "loss": 0.5792, + "step": 879 + }, + { + "epoch": 2.32, + "learning_rate": 2.566008863150492e-06, + "loss": 0.5783, + "step": 880 + }, + { + "epoch": 2.32, + "learning_rate": 2.546971509187238e-06, + "loss": 0.5811, + "step": 881 + }, + { + "epoch": 2.33, + "learning_rate": 2.5279947268237005e-06, + "loss": 0.5746, + "step": 882 + }, + { + "epoch": 2.33, + "learning_rate": 2.5090786702863126e-06, + "loss": 0.5843, + "step": 883 + }, + { + "epoch": 2.33, + "learning_rate": 2.490223493307997e-06, + "loss": 0.581, + "step": 884 + }, + { + "epoch": 2.33, + "learning_rate": 2.4714293491268904e-06, + "loss": 0.5882, + "step": 885 + }, + { + "epoch": 2.34, + "learning_rate": 2.452696390485114e-06, + "loss": 0.5826, + "step": 886 + }, + { + "epoch": 2.34, + "learning_rate": 2.4340247696275297e-06, + "loss": 0.5806, + "step": 887 + }, + { + "epoch": 2.34, + "learning_rate": 2.4154146383004995e-06, + "loss": 0.5724, + "step": 888 + }, + { + "epoch": 2.34, + "learning_rate": 2.396866147750644e-06, + "loss": 0.5809, + "step": 889 + }, + { + "epoch": 2.35, + "learning_rate": 2.3783794487236367e-06, + "loss": 0.5838, + "step": 890 + }, + { + "epoch": 2.35, + "learning_rate": 2.3599546914629534e-06, + "loss": 0.5704, + "step": 891 + }, + { + "epoch": 2.35, + "learning_rate": 2.3415920257086633e-06, + "loss": 0.5801, + "step": 892 + }, + { + "epoch": 2.35, + "learning_rate": 2.323291600696217e-06, + "loss": 0.5835, + "step": 893 + }, + { + "epoch": 2.36, + "learning_rate": 2.305053565155223e-06, + "loss": 0.5868, + "step": 894 + }, + { + "epoch": 2.36, + "learning_rate": 2.286878067308248e-06, + "loss": 0.5902, + "step": 895 + }, + { + "epoch": 2.36, + "learning_rate": 2.2687652548695993e-06, + "loss": 0.582, + "step": 896 + }, + { + "epoch": 2.36, + "learning_rate": 2.250715275044144e-06, + "loss": 0.5799, + "step": 897 + }, + { + "epoch": 2.37, + "learning_rate": 2.2327282745260893e-06, + "loss": 0.5761, + "step": 898 + }, + { + "epoch": 2.37, + "learning_rate": 2.214804399497815e-06, + "loss": 0.5821, + "step": 899 + }, + { + "epoch": 2.37, + "learning_rate": 2.1969437956286575e-06, + "loss": 0.5702, + "step": 900 + }, + { + "epoch": 2.38, + "learning_rate": 2.179146608073763e-06, + "loss": 0.5865, + "step": 901 + }, + { + "epoch": 2.38, + "learning_rate": 2.1614129814728648e-06, + "loss": 0.5766, + "step": 902 + }, + { + "epoch": 2.38, + "learning_rate": 2.143743059949144e-06, + "loss": 0.5818, + "step": 903 + }, + { + "epoch": 2.38, + "learning_rate": 2.126136987108034e-06, + "loss": 0.5722, + "step": 904 + }, + { + "epoch": 2.39, + "learning_rate": 2.1085949060360654e-06, + "loss": 0.5725, + "step": 905 + }, + { + "epoch": 2.39, + "learning_rate": 2.0911169592997027e-06, + "loss": 0.5779, + "step": 906 + }, + { + "epoch": 2.39, + "learning_rate": 2.073703288944183e-06, + "loss": 0.5826, + "step": 907 + }, + { + "epoch": 2.39, + "learning_rate": 2.056354036492363e-06, + "loss": 0.5777, + "step": 908 + }, + { + "epoch": 2.4, + "learning_rate": 2.0390693429435626e-06, + "loss": 0.5875, + "step": 909 + }, + { + "epoch": 2.4, + "learning_rate": 2.021849348772431e-06, + "loss": 0.5782, + "step": 910 + }, + { + "epoch": 2.4, + "learning_rate": 2.004694193927791e-06, + "loss": 0.5769, + "step": 911 + }, + { + "epoch": 2.4, + "learning_rate": 1.9876040178315194e-06, + "loss": 0.5811, + "step": 912 + }, + { + "epoch": 2.41, + "learning_rate": 1.970578959377388e-06, + "loss": 0.5903, + "step": 913 + }, + { + "epoch": 2.41, + "learning_rate": 1.9536191569299666e-06, + "loss": 0.5872, + "step": 914 + }, + { + "epoch": 2.41, + "learning_rate": 1.9367247483234743e-06, + "loss": 0.5797, + "step": 915 + }, + { + "epoch": 2.41, + "learning_rate": 1.919895870860662e-06, + "loss": 0.5771, + "step": 916 + }, + { + "epoch": 2.42, + "learning_rate": 1.903132661311714e-06, + "loss": 0.5915, + "step": 917 + }, + { + "epoch": 2.42, + "learning_rate": 1.8864352559131116e-06, + "loss": 0.5827, + "step": 918 + }, + { + "epoch": 2.42, + "learning_rate": 1.8698037903665479e-06, + "loss": 0.58, + "step": 919 + }, + { + "epoch": 2.43, + "learning_rate": 1.853238399837809e-06, + "loss": 0.5833, + "step": 920 + }, + { + "epoch": 2.43, + "learning_rate": 1.8367392189556843e-06, + "loss": 0.5775, + "step": 921 + }, + { + "epoch": 2.43, + "learning_rate": 1.8203063818108724e-06, + "loss": 0.5776, + "step": 922 + }, + { + "epoch": 2.43, + "learning_rate": 1.8039400219548876e-06, + "loss": 0.5794, + "step": 923 + }, + { + "epoch": 2.44, + "learning_rate": 1.7876402723989695e-06, + "loss": 0.5881, + "step": 924 + }, + { + "epoch": 2.44, + "learning_rate": 1.7714072656130199e-06, + "loss": 0.5831, + "step": 925 + }, + { + "epoch": 2.44, + "learning_rate": 1.7552411335245056e-06, + "loss": 0.5791, + "step": 926 + }, + { + "epoch": 2.44, + "learning_rate": 1.7391420075173915e-06, + "loss": 0.5816, + "step": 927 + }, + { + "epoch": 2.45, + "learning_rate": 1.7231100184310955e-06, + "loss": 0.5729, + "step": 928 + }, + { + "epoch": 2.45, + "learning_rate": 1.7071452965593839e-06, + "loss": 0.577, + "step": 929 + }, + { + "epoch": 2.45, + "learning_rate": 1.6912479716493512e-06, + "loss": 0.5858, + "step": 930 + }, + { + "epoch": 2.45, + "learning_rate": 1.675418172900336e-06, + "loss": 0.5747, + "step": 931 + }, + { + "epoch": 2.46, + "learning_rate": 1.6596560289628983e-06, + "loss": 0.5825, + "step": 932 + }, + { + "epoch": 2.46, + "learning_rate": 1.6439616679377445e-06, + "loss": 0.5763, + "step": 933 + }, + { + "epoch": 2.46, + "learning_rate": 1.6283352173747148e-06, + "loss": 0.5758, + "step": 934 + }, + { + "epoch": 2.46, + "learning_rate": 1.6127768042717252e-06, + "loss": 0.5808, + "step": 935 + }, + { + "epoch": 2.47, + "learning_rate": 1.5972865550737516e-06, + "loss": 0.5824, + "step": 936 + }, + { + "epoch": 2.47, + "learning_rate": 1.5818645956717827e-06, + "loss": 0.5798, + "step": 937 + }, + { + "epoch": 2.47, + "learning_rate": 1.5665110514018211e-06, + "loss": 0.5855, + "step": 938 + }, + { + "epoch": 2.48, + "learning_rate": 1.5512260470438422e-06, + "loss": 0.5887, + "step": 939 + }, + { + "epoch": 2.48, + "learning_rate": 1.5360097068207902e-06, + "loss": 0.5814, + "step": 940 + }, + { + "epoch": 2.48, + "learning_rate": 1.5208621543975766e-06, + "loss": 0.5807, + "step": 941 + }, + { + "epoch": 2.48, + "learning_rate": 1.5057835128800579e-06, + "loss": 0.5832, + "step": 942 + }, + { + "epoch": 2.49, + "learning_rate": 1.4907739048140524e-06, + "loss": 0.5793, + "step": 943 + }, + { + "epoch": 2.49, + "learning_rate": 1.4758334521843242e-06, + "loss": 0.5796, + "step": 944 + }, + { + "epoch": 2.49, + "learning_rate": 1.4609622764136155e-06, + "loss": 0.5816, + "step": 945 + }, + { + "epoch": 2.49, + "learning_rate": 1.4461604983616385e-06, + "loss": 0.5812, + "step": 946 + }, + { + "epoch": 2.5, + "learning_rate": 1.4314282383241097e-06, + "loss": 0.5756, + "step": 947 + }, + { + "epoch": 2.5, + "learning_rate": 1.4167656160317567e-06, + "loss": 0.5837, + "step": 948 + }, + { + "epoch": 2.5, + "learning_rate": 1.40217275064936e-06, + "loss": 0.5868, + "step": 949 + }, + { + "epoch": 2.5, + "learning_rate": 1.3876497607747774e-06, + "loss": 0.5728, + "step": 950 + }, + { + "epoch": 2.51, + "learning_rate": 1.3731967644379761e-06, + "loss": 0.5776, + "step": 951 + }, + { + "epoch": 2.51, + "learning_rate": 1.3588138791000838e-06, + "loss": 0.5861, + "step": 952 + }, + { + "epoch": 2.51, + "learning_rate": 1.3445012216524223e-06, + "loss": 0.5612, + "step": 953 + }, + { + "epoch": 2.52, + "learning_rate": 1.3302589084155692e-06, + "loss": 0.5837, + "step": 954 + }, + { + "epoch": 2.52, + "learning_rate": 1.3160870551383975e-06, + "loss": 0.5848, + "step": 955 + }, + { + "epoch": 2.52, + "learning_rate": 1.30198577699716e-06, + "loss": 0.5793, + "step": 956 + }, + { + "epoch": 2.52, + "learning_rate": 1.287955188594522e-06, + "loss": 0.582, + "step": 957 + }, + { + "epoch": 2.53, + "learning_rate": 1.2739954039586545e-06, + "loss": 0.5844, + "step": 958 + }, + { + "epoch": 2.53, + "learning_rate": 1.2601065365422915e-06, + "loss": 0.5829, + "step": 959 + }, + { + "epoch": 2.53, + "learning_rate": 1.2462886992218238e-06, + "loss": 0.5803, + "step": 960 + }, + { + "epoch": 2.53, + "learning_rate": 1.232542004296362e-06, + "loss": 0.5789, + "step": 961 + }, + { + "epoch": 2.54, + "learning_rate": 1.2188665634868424e-06, + "loss": 0.5808, + "step": 962 + }, + { + "epoch": 2.54, + "learning_rate": 1.2052624879351105e-06, + "loss": 0.5773, + "step": 963 + }, + { + "epoch": 2.54, + "learning_rate": 1.1917298882030115e-06, + "loss": 0.5763, + "step": 964 + }, + { + "epoch": 2.54, + "learning_rate": 1.1782688742715098e-06, + "loss": 0.5757, + "step": 965 + }, + { + "epoch": 2.55, + "learning_rate": 1.1648795555397719e-06, + "loss": 0.5868, + "step": 966 + }, + { + "epoch": 2.55, + "learning_rate": 1.1515620408242989e-06, + "loss": 0.5838, + "step": 967 + }, + { + "epoch": 2.55, + "learning_rate": 1.1383164383580248e-06, + "loss": 0.5791, + "step": 968 + }, + { + "epoch": 2.55, + "learning_rate": 1.1251428557894516e-06, + "loss": 0.5764, + "step": 969 + }, + { + "epoch": 2.56, + "learning_rate": 1.1120414001817647e-06, + "loss": 0.5737, + "step": 970 + }, + { + "epoch": 2.56, + "learning_rate": 1.0990121780119668e-06, + "loss": 0.579, + "step": 971 + }, + { + "epoch": 2.56, + "learning_rate": 1.0860552951700054e-06, + "loss": 0.5785, + "step": 972 + }, + { + "epoch": 2.57, + "learning_rate": 1.073170856957928e-06, + "loss": 0.5838, + "step": 973 + }, + { + "epoch": 2.57, + "learning_rate": 1.060358968089008e-06, + "loss": 0.5762, + "step": 974 + }, + { + "epoch": 2.57, + "learning_rate": 1.0476197326869043e-06, + "loss": 0.5786, + "step": 975 + }, + { + "epoch": 2.57, + "learning_rate": 1.0349532542848162e-06, + "loss": 0.5862, + "step": 976 + }, + { + "epoch": 2.58, + "learning_rate": 1.0223596358246346e-06, + "loss": 0.5856, + "step": 977 + }, + { + "epoch": 2.58, + "learning_rate": 1.0098389796561158e-06, + "loss": 0.5732, + "step": 978 + }, + { + "epoch": 2.58, + "learning_rate": 9.973913875360331e-07, + "loss": 0.5748, + "step": 979 + }, + { + "epoch": 2.58, + "learning_rate": 9.850169606273708e-07, + "loss": 0.5779, + "step": 980 + }, + { + "epoch": 2.59, + "learning_rate": 9.727157994984815e-07, + "loss": 0.579, + "step": 981 + }, + { + "epoch": 2.59, + "learning_rate": 9.604880041222854e-07, + "loss": 0.5798, + "step": 982 + }, + { + "epoch": 2.59, + "learning_rate": 9.4833367387545e-07, + "loss": 0.5804, + "step": 983 + }, + { + "epoch": 2.59, + "learning_rate": 9.362529075375848e-07, + "loss": 0.5731, + "step": 984 + }, + { + "epoch": 2.6, + "learning_rate": 9.242458032904311e-07, + "loss": 0.5738, + "step": 985 + }, + { + "epoch": 2.6, + "learning_rate": 9.123124587170728e-07, + "loss": 0.5695, + "step": 986 + }, + { + "epoch": 2.6, + "learning_rate": 9.004529708011455e-07, + "loss": 0.5843, + "step": 987 + }, + { + "epoch": 2.6, + "learning_rate": 8.88667435926035e-07, + "loss": 0.5733, + "step": 988 + }, + { + "epoch": 2.61, + "learning_rate": 8.769559498741109e-07, + "loss": 0.5767, + "step": 989 + }, + { + "epoch": 2.61, + "learning_rate": 8.653186078259346e-07, + "loss": 0.579, + "step": 990 + }, + { + "epoch": 2.61, + "learning_rate": 8.537555043594936e-07, + "loss": 0.5761, + "step": 991 + }, + { + "epoch": 2.62, + "learning_rate": 8.42266733449425e-07, + "loss": 0.5817, + "step": 992 + }, + { + "epoch": 2.62, + "learning_rate": 8.308523884662656e-07, + "loss": 0.5879, + "step": 993 + }, + { + "epoch": 2.62, + "learning_rate": 8.195125621756739e-07, + "loss": 0.5718, + "step": 994 + }, + { + "epoch": 2.62, + "learning_rate": 8.08247346737695e-07, + "loss": 0.5724, + "step": 995 + }, + { + "epoch": 2.63, + "learning_rate": 7.970568337059992e-07, + "loss": 0.5724, + "step": 996 + }, + { + "epoch": 2.63, + "learning_rate": 7.859411140271422e-07, + "loss": 0.5789, + "step": 997 + }, + { + "epoch": 2.63, + "learning_rate": 7.749002780398295e-07, + "loss": 0.5828, + "step": 998 + }, + { + "epoch": 2.63, + "learning_rate": 7.639344154741713e-07, + "loss": 0.5803, + "step": 999 + }, + { + "epoch": 2.64, + "learning_rate": 7.530436154509679e-07, + "loss": 0.5707, + "step": 1000 + }, + { + "epoch": 2.64, + "learning_rate": 7.422279664809706e-07, + "loss": 0.588, + "step": 1001 + }, + { + "epoch": 2.64, + "learning_rate": 7.314875564641777e-07, + "loss": 0.5756, + "step": 1002 + }, + { + "epoch": 2.64, + "learning_rate": 7.208224726891044e-07, + "loss": 0.5787, + "step": 1003 + }, + { + "epoch": 2.65, + "learning_rate": 7.102328018320859e-07, + "loss": 0.5688, + "step": 1004 + }, + { + "epoch": 2.65, + "learning_rate": 6.997186299565661e-07, + "loss": 0.5799, + "step": 1005 + }, + { + "epoch": 2.65, + "learning_rate": 6.892800425124035e-07, + "loss": 0.5768, + "step": 1006 + }, + { + "epoch": 2.65, + "learning_rate": 6.789171243351678e-07, + "loss": 0.5747, + "step": 1007 + }, + { + "epoch": 2.66, + "learning_rate": 6.686299596454604e-07, + "loss": 0.5741, + "step": 1008 + }, + { + "epoch": 2.66, + "learning_rate": 6.584186320482222e-07, + "loss": 0.5823, + "step": 1009 + }, + { + "epoch": 2.66, + "learning_rate": 6.482832245320625e-07, + "loss": 0.5801, + "step": 1010 + }, + { + "epoch": 2.67, + "learning_rate": 6.382238194685752e-07, + "loss": 0.581, + "step": 1011 + }, + { + "epoch": 2.67, + "learning_rate": 6.282404986116752e-07, + "loss": 0.5746, + "step": 1012 + }, + { + "epoch": 2.67, + "learning_rate": 6.18333343096933e-07, + "loss": 0.5813, + "step": 1013 + }, + { + "epoch": 2.67, + "learning_rate": 6.08502433440914e-07, + "loss": 0.5734, + "step": 1014 + }, + { + "epoch": 2.68, + "learning_rate": 5.987478495405252e-07, + "loss": 0.5803, + "step": 1015 + }, + { + "epoch": 2.68, + "learning_rate": 5.890696706723642e-07, + "loss": 0.5775, + "step": 1016 + }, + { + "epoch": 2.68, + "learning_rate": 5.794679754920796e-07, + "loss": 0.5712, + "step": 1017 + }, + { + "epoch": 2.68, + "learning_rate": 5.699428420337261e-07, + "loss": 0.5803, + "step": 1018 + }, + { + "epoch": 2.69, + "learning_rate": 5.604943477091351e-07, + "loss": 0.5704, + "step": 1019 + }, + { + "epoch": 2.69, + "learning_rate": 5.511225693072797e-07, + "loss": 0.5747, + "step": 1020 + }, + { + "epoch": 2.69, + "learning_rate": 5.418275829936537e-07, + "loss": 0.58, + "step": 1021 + }, + { + "epoch": 2.69, + "learning_rate": 5.32609464309658e-07, + "loss": 0.5792, + "step": 1022 + }, + { + "epoch": 2.7, + "learning_rate": 5.234682881719766e-07, + "loss": 0.5756, + "step": 1023 + }, + { + "epoch": 2.7, + "learning_rate": 5.144041288719747e-07, + "loss": 0.5775, + "step": 1024 + }, + { + "epoch": 2.7, + "learning_rate": 5.05417060075094e-07, + "loss": 0.5825, + "step": 1025 + }, + { + "epoch": 2.7, + "learning_rate": 4.965071548202538e-07, + "loss": 0.5771, + "step": 1026 + }, + { + "epoch": 2.71, + "learning_rate": 4.876744855192516e-07, + "loss": 0.5844, + "step": 1027 + }, + { + "epoch": 2.71, + "learning_rate": 4.789191239561852e-07, + "loss": 0.5794, + "step": 1028 + }, + { + "epoch": 2.71, + "learning_rate": 4.7024114128686017e-07, + "loss": 0.5857, + "step": 1029 + }, + { + "epoch": 2.72, + "learning_rate": 4.616406080382174e-07, + "loss": 0.5832, + "step": 1030 + }, + { + "epoch": 2.72, + "learning_rate": 4.531175941077537e-07, + "loss": 0.573, + "step": 1031 + }, + { + "epoch": 2.72, + "learning_rate": 4.4467216876296625e-07, + "loss": 0.5825, + "step": 1032 + }, + { + "epoch": 2.72, + "learning_rate": 4.363044006407724e-07, + "loss": 0.5805, + "step": 1033 + }, + { + "epoch": 2.73, + "learning_rate": 4.28014357746962e-07, + "loss": 0.5836, + "step": 1034 + }, + { + "epoch": 2.73, + "learning_rate": 4.198021074556469e-07, + "loss": 0.5786, + "step": 1035 + }, + { + "epoch": 2.73, + "learning_rate": 4.1166771650870687e-07, + "loss": 0.5712, + "step": 1036 + }, + { + "epoch": 2.73, + "learning_rate": 4.0361125101525124e-07, + "loss": 0.5753, + "step": 1037 + }, + { + "epoch": 2.74, + "learning_rate": 3.956327764510792e-07, + "loss": 0.5764, + "step": 1038 + }, + { + "epoch": 2.74, + "learning_rate": 3.8773235765815155e-07, + "loss": 0.5785, + "step": 1039 + }, + { + "epoch": 2.74, + "learning_rate": 3.799100588440574e-07, + "loss": 0.5748, + "step": 1040 + }, + { + "epoch": 2.74, + "learning_rate": 3.721659435814995e-07, + "loss": 0.5749, + "step": 1041 + }, + { + "epoch": 2.75, + "learning_rate": 3.645000748077709e-07, + "loss": 0.5708, + "step": 1042 + }, + { + "epoch": 2.75, + "learning_rate": 3.5691251482424914e-07, + "loss": 0.5824, + "step": 1043 + }, + { + "epoch": 2.75, + "learning_rate": 3.4940332529588506e-07, + "loss": 0.5802, + "step": 1044 + }, + { + "epoch": 2.75, + "learning_rate": 3.419725672507068e-07, + "loss": 0.5772, + "step": 1045 + }, + { + "epoch": 2.76, + "learning_rate": 3.346203010793203e-07, + "loss": 0.5756, + "step": 1046 + }, + { + "epoch": 2.76, + "learning_rate": 3.273465865344172e-07, + "loss": 0.5849, + "step": 1047 + }, + { + "epoch": 2.76, + "learning_rate": 3.201514827302943e-07, + "loss": 0.579, + "step": 1048 + }, + { + "epoch": 2.77, + "learning_rate": 3.1303504814236494e-07, + "loss": 0.583, + "step": 1049 + }, + { + "epoch": 2.77, + "learning_rate": 3.059973406066963e-07, + "loss": 0.573, + "step": 1050 + }, + { + "epoch": 2.77, + "learning_rate": 2.99038417319526e-07, + "loss": 0.5805, + "step": 1051 + }, + { + "epoch": 2.77, + "learning_rate": 2.921583348368051e-07, + "loss": 0.574, + "step": 1052 + }, + { + "epoch": 2.78, + "learning_rate": 2.853571490737372e-07, + "loss": 0.5788, + "step": 1053 + }, + { + "epoch": 2.78, + "learning_rate": 2.786349153043244e-07, + "loss": 0.5774, + "step": 1054 + }, + { + "epoch": 2.78, + "learning_rate": 2.7199168816091416e-07, + "loss": 0.5787, + "step": 1055 + }, + { + "epoch": 2.78, + "learning_rate": 2.6542752163375876e-07, + "loss": 0.5728, + "step": 1056 + }, + { + "epoch": 2.79, + "learning_rate": 2.589424690705777e-07, + "loss": 0.5748, + "step": 1057 + }, + { + "epoch": 2.79, + "learning_rate": 2.525365831761217e-07, + "loss": 0.5749, + "step": 1058 + }, + { + "epoch": 2.79, + "learning_rate": 2.4620991601174596e-07, + "loss": 0.5768, + "step": 1059 + }, + { + "epoch": 2.79, + "learning_rate": 2.399625189949839e-07, + "loss": 0.5769, + "step": 1060 + }, + { + "epoch": 2.8, + "learning_rate": 2.3379444289913344e-07, + "loss": 0.5835, + "step": 1061 + }, + { + "epoch": 2.8, + "learning_rate": 2.2770573785284133e-07, + "loss": 0.579, + "step": 1062 + }, + { + "epoch": 2.8, + "learning_rate": 2.2169645333969815e-07, + "loss": 0.5781, + "step": 1063 + }, + { + "epoch": 2.81, + "learning_rate": 2.1576663819783295e-07, + "loss": 0.5776, + "step": 1064 + }, + { + "epoch": 2.81, + "learning_rate": 2.0991634061952038e-07, + "loss": 0.5724, + "step": 1065 + }, + { + "epoch": 2.81, + "learning_rate": 2.0414560815078533e-07, + "loss": 0.5867, + "step": 1066 + }, + { + "epoch": 2.81, + "learning_rate": 1.9845448769102105e-07, + "loss": 0.5799, + "step": 1067 + }, + { + "epoch": 2.82, + "learning_rate": 1.928430254926006e-07, + "loss": 0.5792, + "step": 1068 + }, + { + "epoch": 2.82, + "learning_rate": 1.8731126716050707e-07, + "loss": 0.5837, + "step": 1069 + }, + { + "epoch": 2.82, + "learning_rate": 1.818592576519629e-07, + "loss": 0.5743, + "step": 1070 + }, + { + "epoch": 2.82, + "learning_rate": 1.764870412760611e-07, + "loss": 0.5742, + "step": 1071 + }, + { + "epoch": 2.83, + "learning_rate": 1.7119466169340794e-07, + "loss": 0.5819, + "step": 1072 + }, + { + "epoch": 2.83, + "learning_rate": 1.6598216191576643e-07, + "loss": 0.5744, + "step": 1073 + }, + { + "epoch": 2.83, + "learning_rate": 1.6084958430571006e-07, + "loss": 0.573, + "step": 1074 + }, + { + "epoch": 2.83, + "learning_rate": 1.5579697057627074e-07, + "loss": 0.5819, + "step": 1075 + }, + { + "epoch": 2.84, + "learning_rate": 1.508243617906091e-07, + "loss": 0.58, + "step": 1076 + }, + { + "epoch": 2.84, + "learning_rate": 1.459317983616737e-07, + "loss": 0.5815, + "step": 1077 + }, + { + "epoch": 2.84, + "learning_rate": 1.411193200518801e-07, + "loss": 0.5715, + "step": 1078 + }, + { + "epoch": 2.84, + "learning_rate": 1.3638696597277678e-07, + "loss": 0.5726, + "step": 1079 + }, + { + "epoch": 2.85, + "learning_rate": 1.317347745847386e-07, + "loss": 0.5774, + "step": 1080 + }, + { + "epoch": 2.85, + "learning_rate": 1.2716278369664825e-07, + "loss": 0.58, + "step": 1081 + }, + { + "epoch": 2.85, + "learning_rate": 1.226710304655876e-07, + "loss": 0.5754, + "step": 1082 + }, + { + "epoch": 2.86, + "learning_rate": 1.1825955139654121e-07, + "loss": 0.5837, + "step": 1083 + }, + { + "epoch": 2.86, + "learning_rate": 1.1392838234209336e-07, + "loss": 0.589, + "step": 1084 + }, + { + "epoch": 2.86, + "learning_rate": 1.0967755850214257e-07, + "loss": 0.5794, + "step": 1085 + }, + { + "epoch": 2.86, + "learning_rate": 1.0550711442361083e-07, + "loss": 0.5757, + "step": 1086 + }, + { + "epoch": 2.87, + "learning_rate": 1.0141708400016714e-07, + "loss": 0.5755, + "step": 1087 + }, + { + "epoch": 2.87, + "learning_rate": 9.74075004719477e-08, + "loss": 0.5738, + "step": 1088 + }, + { + "epoch": 2.87, + "learning_rate": 9.347839642528721e-08, + "loss": 0.5751, + "step": 1089 + }, + { + "epoch": 2.87, + "learning_rate": 8.962980379245589e-08, + "loss": 0.5811, + "step": 1090 + }, + { + "epoch": 2.88, + "learning_rate": 8.58617538513995e-08, + "loss": 0.5804, + "step": 1091 + }, + { + "epoch": 2.88, + "learning_rate": 8.217427722548077e-08, + "loss": 0.5866, + "step": 1092 + }, + { + "epoch": 2.88, + "learning_rate": 7.856740388323847e-08, + "loss": 0.5818, + "step": 1093 + }, + { + "epoch": 2.88, + "learning_rate": 7.504116313813759e-08, + "loss": 0.5878, + "step": 1094 + }, + { + "epoch": 2.89, + "learning_rate": 7.159558364833175e-08, + "loss": 0.581, + "step": 1095 + }, + { + "epoch": 2.89, + "learning_rate": 6.823069341643341e-08, + "loss": 0.5714, + "step": 1096 + }, + { + "epoch": 2.89, + "learning_rate": 6.494651978928179e-08, + "loss": 0.5755, + "step": 1097 + }, + { + "epoch": 2.89, + "learning_rate": 6.174308945772644e-08, + "loss": 0.5787, + "step": 1098 + }, + { + "epoch": 2.9, + "learning_rate": 5.862042845640403e-08, + "loss": 0.5689, + "step": 1099 + }, + { + "epoch": 2.9, + "learning_rate": 5.557856216353297e-08, + "loss": 0.5812, + "step": 1100 + }, + { + "epoch": 2.9, + "learning_rate": 5.261751530070136e-08, + "loss": 0.5773, + "step": 1101 + }, + { + "epoch": 2.91, + "learning_rate": 4.9737311932669395e-08, + "loss": 0.574, + "step": 1102 + }, + { + "epoch": 2.91, + "learning_rate": 4.693797546717505e-08, + "loss": 0.5809, + "step": 1103 + }, + { + "epoch": 2.91, + "learning_rate": 4.421952865473755e-08, + "loss": 0.5794, + "step": 1104 + }, + { + "epoch": 2.91, + "learning_rate": 4.1581993588482025e-08, + "loss": 0.5788, + "step": 1105 + }, + { + "epoch": 2.92, + "learning_rate": 3.90253917039507e-08, + "loss": 0.578, + "step": 1106 + }, + { + "epoch": 2.92, + "learning_rate": 3.6549743778934166e-08, + "loss": 0.5771, + "step": 1107 + }, + { + "epoch": 2.92, + "learning_rate": 3.4155069933301535e-08, + "loss": 0.5818, + "step": 1108 + }, + { + "epoch": 2.92, + "learning_rate": 3.18413896288372e-08, + "loss": 0.5699, + "step": 1109 + }, + { + "epoch": 2.93, + "learning_rate": 2.96087216690788e-08, + "loss": 0.576, + "step": 1110 + }, + { + "epoch": 2.93, + "learning_rate": 2.74570841991717e-08, + "loss": 0.5816, + "step": 1111 + }, + { + "epoch": 2.93, + "learning_rate": 2.5386494705713638e-08, + "loss": 0.5843, + "step": 1112 + }, + { + "epoch": 2.93, + "learning_rate": 2.3396970016619225e-08, + "loss": 0.5765, + "step": 1113 + }, + { + "epoch": 2.94, + "learning_rate": 2.1488526300978972e-08, + "loss": 0.5745, + "step": 1114 + }, + { + "epoch": 2.94, + "learning_rate": 1.9661179068928283e-08, + "loss": 0.5851, + "step": 1115 + }, + { + "epoch": 2.94, + "learning_rate": 1.791494317152531e-08, + "loss": 0.583, + "step": 1116 + }, + { + "epoch": 2.94, + "learning_rate": 1.624983280062331e-08, + "loss": 0.5796, + "step": 1117 + }, + { + "epoch": 2.95, + "learning_rate": 1.4665861488761813e-08, + "loss": 0.5775, + "step": 1118 + }, + { + "epoch": 2.95, + "learning_rate": 1.3163042109053393e-08, + "loss": 0.578, + "step": 1119 + }, + { + "epoch": 2.95, + "learning_rate": 1.1741386875081528e-08, + "loss": 0.5808, + "step": 1120 + }, + { + "epoch": 2.96, + "learning_rate": 1.040090734079624e-08, + "loss": 0.5815, + "step": 1121 + }, + { + "epoch": 2.96, + "learning_rate": 9.14161440042527e-09, + "loss": 0.5852, + "step": 1122 + }, + { + "epoch": 2.96, + "learning_rate": 7.963518288385264e-09, + "loss": 0.5739, + "step": 1123 + }, + { + "epoch": 2.96, + "learning_rate": 6.866628579195178e-09, + "loss": 0.5825, + "step": 1124 + }, + { + "epoch": 2.97, + "learning_rate": 5.850954187399671e-09, + "loss": 0.5807, + "step": 1125 + }, + { + "epoch": 2.97, + "learning_rate": 4.91650336750027e-09, + "loss": 0.5837, + "step": 1126 + }, + { + "epoch": 2.97, + "learning_rate": 4.063283713883203e-09, + "loss": 0.5748, + "step": 1127 + }, + { + "epoch": 2.97, + "learning_rate": 3.2913021607594574e-09, + "loss": 0.5764, + "step": 1128 + }, + { + "epoch": 2.98, + "learning_rate": 2.600564982110365e-09, + "loss": 0.573, + "step": 1129 + }, + { + "epoch": 2.98, + "learning_rate": 1.9910777916354316e-09, + "loss": 0.5839, + "step": 1130 + }, + { + "epoch": 2.98, + "learning_rate": 1.462845542704594e-09, + "loss": 0.5807, + "step": 1131 + }, + { + "epoch": 2.98, + "learning_rate": 1.0158725283204718e-09, + "loss": 0.5857, + "step": 1132 + }, + { + "epoch": 2.99, + "learning_rate": 6.50162381083952e-10, + "loss": 0.5813, + "step": 1133 + }, + { + "epoch": 2.99, + "learning_rate": 3.6571807316199135e-10, + "loss": 0.5791, + "step": 1134 + }, + { + "epoch": 2.99, + "learning_rate": 1.6254191626430272e-10, + "loss": 0.5773, + "step": 1135 + }, + { + "epoch": 2.99, + "learning_rate": 4.063556162892113e-11, + "loss": 0.5774, + "step": 1136 + }, + { + "epoch": 3.0, + "learning_rate": 0.0, + "loss": 0.5688, + "step": 1137 + }, + { + "epoch": 3.0, + "step": 1137, + "total_flos": 3.0126552732370207e+18, + "train_loss": 0.646743938392364, + "train_runtime": 27308.2637, + "train_samples_per_second": 10.668, + "train_steps_per_second": 0.042 + } + ], + "max_steps": 1137, + "num_train_epochs": 3, + "total_flos": 3.0126552732370207e+18, + "trial_name": null, + "trial_params": null +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000..e1067a5 --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41b6fc1998be406fe8d6ad5198efb8a08818919fa87e27b470afd6d68fb23276 +size 3771